Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDSearch dblp for Publications
export results for "html document"
download as .bib file
@article{DBLP:journals/jips/HwangPS23,
author = {Hyun Cheon Hwang and
Ji Su Park and
Jin Gon Shon},
title = {Design and Implementation of the Document {HTML} System for Preserving
Content Integrity},
journal = {J. Inf. Process. Syst.},
volume = {19},
number = {3},
pages = {334--346},
year = {2023},
url = {https://doi.org/10.3745/JIPS.04.0276},
doi = {10.3745/JIPS.04.0276},
timestamp = {Tue, 08 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jips/HwangPS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2201-10608,
author = {Xiang Deng and
Prashant Shiralkar and
Colin Lockard and
Binxuan Huang and
Huan Sun},
title = {{DOM-LM:} Learning Generalizable Representations for {HTML} Documents},
journal = {CoRR},
volume = {abs/2201.10608},
year = {2022},
url = {https://arxiv.org/abs/2201.10608},
eprinttype = {arXiv},
eprint = {2201.10608},
timestamp = {Wed, 31 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2201-10608.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sai/BakaoukasB21,
author = {Nikolaos G. Bakaoukas and
Anastasios G. Bakaoukas},
editor = {Kohei Arai},
title = {A Novel Three-Way Merge Algorithm for {HTML/XML} Documents Using a
Hidden Markov Model},
booktitle = {Intelligent Computing - Proceedings of the 2021 Computing Conference,
Volume 1, {SAI} 2021, Virtual Event, 15-16 July, 2021},
series = {Lecture Notes in Networks and Systems},
volume = {283},
pages = {75--101},
publisher = {Springer},
year = {2021},
url = {https://doi.org/10.1007/978-3-030-80119-9\_3},
doi = {10.1007/978-3-030-80119-9\_3},
timestamp = {Tue, 21 Feb 2023 10:40:01 +0100},
biburl = {https://dblp.org/rec/conf/sai/BakaoukasB21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2112-00962,
author = {Majid Jaberi Douraki and
Soudabeh Taghian Dinani and
Nuwan Indika Millagaha Gedara and
Xuan Xu and
Emily Richards and
Fiona Maunsell and
Nader Zad and
Lisa Ann Tell},
title = {Large-Scale Data Mining of Rapid Residue Detection Assay Data From
{HTML} and {PDF} Documents: Improving Data Access and Visualization
for Veterinarians},
journal = {CoRR},
volume = {abs/2112.00962},
year = {2021},
url = {https://arxiv.org/abs/2112.00962},
eprinttype = {arXiv},
eprint = {2112.00962},
timestamp = {Tue, 07 Dec 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2112-00962.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nbis/MaruyamaONYK20,
author = {Koki Maruyama and
Yasuhiro Ohtaki and
Michitoshi Niibori and
Tatsuhiro Yonekura and
Masaru Kamada},
editor = {Leonard Barolli and
Kin Fun Li and
Tomoya Enokido and
Makoto Takizawa},
title = {Another {HTML5} Implementation of Web-Com for Embedding Chalk Annotations
and Talk Voices into {HTML} Documents},
booktitle = {Advances in Networked-Based Information Systems - The 23rd International
Conference on Network-Based Information Systems, NBiS 2020, Victoria,
BC, Canada, 31 August - 2 September 2020},
series = {Advances in Intelligent Systems and Computing},
volume = {1264},
pages = {560--566},
publisher = {Springer},
year = {2020},
url = {https://doi.org/10.1007/978-3-030-57811-4\_56},
doi = {10.1007/978-3-030-57811-4\_56},
timestamp = {Fri, 21 Aug 2020 15:16:47 +0200},
biburl = {https://dblp.org/rec/conf/nbis/MaruyamaONYK20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sai/BakaoukasB20,
author = {Anastasios G. Bakaoukas and
Nikolaos G. Bakaoukas},
editor = {Kohei Arai and
Supriya Kapoor and
Rahul Bhatia},
title = {A Top-Down Three-Way Merge Algorithm for {HTML/XML} Documents},
booktitle = {Intelligent Computing - Proceedings of the 2020 Computing Conference,
Volume 1, {SAI} 2020, London, UK, 16-17 July 2020},
series = {Advances in Intelligent Systems and Computing},
volume = {1228},
pages = {75--96},
publisher = {Springer},
year = {2020},
url = {https://doi.org/10.1007/978-3-030-52249-0\_6},
doi = {10.1007/978-3-030-52249-0\_6},
timestamp = {Tue, 07 Jul 2020 14:30:18 +0200},
biburl = {https://dblp.org/rec/conf/sai/BakaoukasB20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/vl/SchmollVSSC18,
author = {Steven Schmoll and
Anith Vishwanath and
Mohammad Ammar Siddiqui and
Boppaiah Koothanda Subbaiah and
Caslon Chua},
editor = {J{\'{a}}come Cunha and
Jo{\~{a}}o Paulo Fernandes and
Caitlin Kelleher and
Gregor Engels and
Jorge Mendes},
title = {{HTML} Document Error Detector and Visualiser for Novice Programmers},
booktitle = {2018 {IEEE} Symposium on Visual Languages and Human-Centric Computing,
{VL/HCC} 2018, Lisbon, Portugal, October 1-4, 2018},
pages = {291--292},
publisher = {{IEEE} Computer Society},
year = {2018},
url = {https://doi.org/10.1109/VLHCC.2018.8506569},
doi = {10.1109/VLHCC.2018.8506569},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/vl/SchmollVSSC18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1801-08928,
author = {Jinqiu Yang and
Erik Wittern and
Annie T. T. Ying and
Julian Dolby and
Lin Tan},
title = {Automatically Extracting Web {API} Specifications from {HTML} Documentation},
journal = {CoRR},
volume = {abs/1801.08928},
year = {2018},
url = {http://arxiv.org/abs/1801.08928},
eprinttype = {arXiv},
eprint = {1801.08928},
timestamp = {Sun, 23 Jun 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1801-08928.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icsoc/CaoFB17,
author = {Hanyang Cao and
Jean{-}R{\'{e}}my Falleri and
Xavier Blanc},
editor = {E. Michael Maximilien and
Antonio Vallecillo and
Jianmin Wang and
Marc Oriol},
title = {Automated Generation of {REST} {API} Specification from Plain {HTML}
Documentation},
booktitle = {Service-Oriented Computing - 15th International Conference, {ICSOC}
2017, Malaga, Spain, November 13-16, 2017, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {10601},
pages = {453--461},
publisher = {Springer},
year = {2017},
url = {https://doi.org/10.1007/978-3-319-69035-3\_32},
doi = {10.1007/978-3-319-69035-3\_32},
timestamp = {Tue, 12 Sep 2023 07:57:22 +0200},
biburl = {https://dblp.org/rec/conf/icsoc/CaoFB17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/lht/VallezPCBR15,
author = {Mari Vallez and
Rafael Pedraza{-}Jimenez and
Llu{\'{\i}}s Codina and
Sa{\'{u}}l Blanco and
Crist{\`{o}}fol Rovira},
title = {A semi-automatic indexing system based on embedded information in
{HTML} documents},
journal = {Libr. Hi Tech},
volume = {33},
number = {2},
pages = {195--210},
year = {2015},
url = {https://doi.org/10.1108/LHT-12-2014-0114},
doi = {10.1108/LHT-12-2014-0114},
timestamp = {Sat, 05 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/lht/VallezPCBR15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pvldb/ManabeT15,
author = {Tomohiro Manabe and
Keishi Tajima},
title = {Extracting Logical Hierarchical Structure of {HTML} Documents Based
on Headings},
journal = {Proc. {VLDB} Endow.},
volume = {8},
number = {12},
pages = {1606--1617},
year = {2015},
url = {http://www.vldb.org/pvldb/vol8/p1606-manabe.pdf},
doi = {10.14778/2824032.2824058},
timestamp = {Sat, 25 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/pvldb/ManabeT15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/airs/FaghaniHM15,
author = {Shabanali Faghani and
Ali Hadian and
Behrouz Minaei{-}Bidgoli},
editor = {Guido Zuccon and
Shlomo Geva and
Hideo Joho and
Falk Scholer and
Aixin Sun and
Peng Zhang},
title = {Charset Encoding Detection of {HTML} Documents - {A} Practical Experience},
booktitle = {Information Retrieval Technology - 11th Asia Information Retrieval
Societies Conference, {AIRS} 2015, Brisbane, QLD, Australia, December
2-4, 2015. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {9460},
pages = {215--226},
publisher = {Springer},
year = {2015},
url = {https://doi.org/10.1007/978-3-319-28940-3\_17},
doi = {10.1007/978-3-319-28940-3\_17},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/airs/FaghaniHM15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icitcs/PrompilaL15,
author = {Ekarat Prompila and
Yachai Limpiyakorn},
title = {Automating Documentation of {HTML} Prototype},
booktitle = {5th International Conference on {IT} Convergence and Security, {ICITCS}
2015, Kuala Lumpur, Malaysia, August 24-27, 2015},
pages = {1--5},
publisher = {{IEEE} Computer Society},
year = {2015},
url = {https://doi.org/10.1109/ICITCS.2015.7292955},
doi = {10.1109/ICITCS.2015.7292955},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icitcs/PrompilaL15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mkm/NakashoS15,
author = {Kazuhisa Nakasho and
Yasunari Shidama},
editor = {Manfred Kerber and
Jacques Carette and
Cezary Kaliszyk and
Florian Rabe and
Volker Sorge},
title = {Documentation Generator Focusing on Symbols for the HTML-ized Mizar
Library},
booktitle = {Intelligent Computer Mathematics - International Conference, {CICM}
2015, Washington, DC, USA, July 13-17, 2015, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {9150},
pages = {343--347},
publisher = {Springer},
year = {2015},
url = {https://doi.org/10.1007/978-3-319-20615-8\_25},
doi = {10.1007/978-3-319-20615-8\_25},
timestamp = {Fri, 20 Nov 2020 16:08:54 +0100},
biburl = {https://dblp.org/rec/conf/mkm/NakashoS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/NakashoS15,
author = {Kazuhisa Nakasho and
Yasunari Shidama},
title = {Documentation Generator Focusing on Symbols for the HTML-ized Mizar
Library},
journal = {CoRR},
volume = {abs/1505.01577},
year = {2015},
url = {http://arxiv.org/abs/1505.01577},
eprinttype = {arXiv},
eprint = {1505.01577},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/NakashoS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijcistudies/ShanmugavadivuS14,
author = {P. Shanmugavadivu and
P. Sumathy and
A. Vadivel},
title = {Ranking images in web documents based on {HTML} TAGs for image retrieval
from {WWW}},
journal = {Int. J. Comput. Intell. Stud.},
volume = {3},
number = {2/3},
pages = {176--195},
year = {2014},
url = {https://doi.org/10.1504/IJCISTUDIES.2014.062730},
doi = {10.1504/IJCISTUDIES.2014.062730},
timestamp = {Wed, 01 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ijcistudies/ShanmugavadivuS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/das/NagySE14,
author = {George Nagy and
Sharad C. Seth and
David W. Embley},
editor = {Jean{-}Yves Ramel and
Marcus Liwicki and
Jean{-}Marc Ogier and
Koichi Kise and
Ray Smith},
title = {End-to-End Conversion of {HTML} Tables for Populating a Relational
Database},
booktitle = {11th {IAPR} International Workshop on Document Analysis Systems, {DAS}
2014, Tours, France, April 7-10, 2014},
pages = {222--226},
publisher = {{IEEE} Computer Society},
year = {2014},
url = {https://doi.org/10.1109/DAS.2014.9},
doi = {10.1109/DAS.2014.9},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/das/NagySE14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@phdthesis{DBLP:phd/basesearch/Mohammadzadeh13,
author = {Hadi Mohammadzadeh},
title = {Improving Retrieval Accuracy in Main Content Extraction from {HTML}
Web Documents},
school = {Leipzig University, Germany},
year = {2013},
url = {https://nbn-resolving.org/urn:nbn:de:bsz:15-qucosa-130500},
urn = {urn:nbn:de:bsz:15-qucosa-130500},
timestamp = {Wed, 13 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/phd/basesearch/Mohammadzadeh13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/doceng/FerilliER13,
author = {Stefano Ferilli and
Floriana Esposito and
Domenico Redavid},
editor = {Simone Marinai and
Kim Marriott},
title = {Hi-Fi {HTML} rendering of multi-format documents in DoMinUS},
booktitle = {{ACM} Symposium on Document Engineering 2013, DocEng '13, Florence,
Italy, September 10-13, 2013},
pages = {173--176},
publisher = {{ACM}},
year = {2013},
url = {https://doi.org/10.1145/2494266.2494272},
doi = {10.1145/2494266.2494272},
timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/doceng/FerilliER13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/doceng/SilvaSM13,
author = {Esdras Caleb Oliveira Silva and
Joel Andr{\'{e}} Ferreira dos Santos and
D{\'{e}}bora C. Muchaluat{-}Saade},
editor = {Simone Marinai and
Kim Marriott},
title = {{NCL4WEB:} translating {NCL} applications to {HTML5} web pages},
booktitle = {{ACM} Symposium on Document Engineering 2013, DocEng '13, Florence,
Italy, September 10-13, 2013},
pages = {253--262},
publisher = {{ACM}},
year = {2013},
url = {https://doi.org/10.1145/2494266.2494273},
doi = {10.1145/2494266.2494273},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/doceng/SilvaSM13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eisic/GoslinH13,
author = {Kyle Goslin and
Markus Hofmann},
title = {Cross Domain Assessment of Document to {HTML} Conversion Tools to
Quantify Text and Structural Loss during Document Analysis},
booktitle = {2013 European Intelligence and Security Informatics Conference, Uppsala,
Sweden, August 12-14, 2013},
pages = {100--105},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/EISIC.2013.22},
doi = {10.1109/EISIC.2013.22},
timestamp = {Thu, 08 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/eisic/GoslinH13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sas/KimDS13,
author = {Hyunha Kim and
Kyung{-}Goo Doh and
David A. Schmidt},
editor = {Francesco Logozzo and
Manuel F{\"{a}}hndrich},
title = {Static Validation of Dynamically Generated {HTML} Documents Based
on Abstract Parsing and Semantic Processing},
booktitle = {Static Analysis - 20th International Symposium, {SAS} 2013, Seattle,
WA, USA, June 20-22, 2013. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {7935},
pages = {194--214},
publisher = {Springer},
year = {2013},
url = {https://doi.org/10.1007/978-3-642-38856-9\_12},
doi = {10.1007/978-3-642-38856-9\_12},
timestamp = {Tue, 14 May 2019 10:00:52 +0200},
biburl = {https://dblp.org/rec/conf/sas/KimDS13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/fskd/ZengFSH12,
author = {Jun Zeng and
Brendan Flanagan and
Toshihiko Sakai and
Sachio Hirokawa},
title = {Extraction of relevant components using shallow structure of {HTML}
documents},
booktitle = {9th International Conference on Fuzzy Systems and Knowledge Discovery,
{FSKD} 2012, 29-31 May 2012, Chongqing, China},
pages = {1186--1190},
publisher = {{IEEE}},
year = {2012},
url = {https://doi.org/10.1109/FSKD.2012.6234295},
doi = {10.1109/FSKD.2012.6234295},
timestamp = {Wed, 16 Oct 2019 14:14:57 +0200},
biburl = {https://dblp.org/rec/conf/fskd/ZengFSH12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icaart/ZarradDZ12,
author = {Rim Zarrad and
Narjes Doggaz and
Ezzeddine Zagrouba},
editor = {Joaquim Filipe and
Ana L. N. Fred},
title = {Concepts Extraction based on {HTML} Documents Structure},
booktitle = {{ICAART} 2012 - Proceedings of the 4th International Conference on
Agents and Artificial Intelligence, Volume 1 - Artificial Intelligence,
Vilamoura, Algarve, Portugal, 6-8 February, 2012},
pages = {503--506},
publisher = {SciTePress},
year = {2012},
timestamp = {Thu, 03 May 2012 17:45:15 +0200},
biburl = {https://dblp.org/rec/conf/icaart/ZarradDZ12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iticse/Kurmas12b,
author = {Zachary Kurmas},
editor = {Tami Lapidot and
Judith Gal{-}Ezer and
Michael E. Caspersen and
Orit Hazzan},
title = {Kielce: configurable {HTML} course documents},
booktitle = {Annual Conference on Innovation and Technology in Computer Science
Education, ITiCSE '12, Haifa, Israel, July 3-5, 2012},
pages = {403},
publisher = {{ACM}},
year = {2012},
url = {https://doi.org/10.1145/2325296.2325419},
doi = {10.1145/2325296.2325419},
timestamp = {Wed, 10 Mar 2021 13:17:16 +0100},
biburl = {https://dblp.org/rec/conf/iticse/Kurmas12b.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1204-0186,
author = {Youssef Bassil and
Paul Semaan},
title = {Semantic-Sensitive Web Information Retrieval Model for {HTML} Documents},
journal = {CoRR},
volume = {abs/1204.0186},
year = {2012},
url = {http://arxiv.org/abs/1204.0186},
eprinttype = {arXiv},
eprint = {1204.0186},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1204-0186.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cyberc/ZhuYWSRY11,
author = {Yanxu Zhu and
Gang Yin and
Huaimin Wang and
Dianxi Shi and
Xiang Rao and
Lin Yuan},
title = {Efficient Approach for Repeated Patterns Mining Based on Indent Shape
of {HTML} Documents},
booktitle = {2011 International Conference on Cyber-Enabled Distributed Computing
and Knowledge Discovery, CyberC 2011, Beijing, China, October 10-12,
2011},
pages = {32--39},
publisher = {{IEEE} Computer Society},
year = {2011},
url = {https://doi.org/10.1109/CyberC.2011.15},
doi = {10.1109/CYBERC.2011.15},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/cyberc/ZhuYWSRY11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/doceng/BultermanGCMP11,
author = {Dick C. A. Bulterman and
Rodrigo Laiola Guimar{\~{a}}es and
Pablo C{\'{e}}sar and
Ethan V. Munson and
Maria da Gra{\c{c}}a Campos Pimentel},
editor = {Matthew R. B. Hardy and
Frank Wm. Tompa},
title = {Multimedia document processing in an {HTML5} world},
booktitle = {Proceedings of the 2011 {ACM} Symposium on Document Engineering, Mountain
View, CA, USA, September 19-22, 2011},
pages = {273--274},
publisher = {{ACM}},
year = {2011},
url = {https://doi.org/10.1145/2034691.2034747},
doi = {10.1145/2034691.2034747},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/doceng/BultermanGCMP11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/doceng/CazenaveQR11,
author = {Fabien Cazenave and
Vincent Quint and
C{\'{e}}cile Roisin},
editor = {Matthew R. B. Hardy and
Frank Wm. Tompa},
title = {Timesheets.js: when {SMIL} meets {HTML5} and {CSS3}},
booktitle = {Proceedings of the 2011 {ACM} Symposium on Document Engineering, Mountain
View, CA, USA, September 19-22, 2011},
pages = {43--52},
publisher = {{ACM}},
year = {2011},
url = {https://doi.org/10.1145/2034691.2034700},
doi = {10.1145/2034691.2034700},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/doceng/CazenaveQR11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/doceng/Tseng11,
author = {Lendle Chun{-}Hsiung Tseng},
editor = {Matthew R. B. Hardy and
Frank Wm. Tompa},
title = {Developer-friendly annotation-based HTML-to-XML transformation technology},
booktitle = {Proceedings of the 2011 {ACM} Symposium on Document Engineering, Mountain
View, CA, USA, September 19-22, 2011},
pages = {73--76},
publisher = {{ACM}},
year = {2011},
url = {https://doi.org/10.1145/2034691.2034707},
doi = {10.1145/2034691.2034707},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/doceng/Tseng11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijdar/ZouLT10,
author = {Jie Zou and
Daniel X. Le and
George R. Thoma},
title = {Locating and parsing bibliographic references in {HTML} medical articles},
journal = {Int. J. Document Anal. Recognit.},
volume = {13},
number = {2},
pages = {107--119},
year = {2010},
url = {https://doi.org/10.1007/s10032-009-0105-9},
doi = {10.1007/S10032-009-0105-9},
timestamp = {Thu, 13 Aug 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ijdar/ZouLT10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/doceng/Piotrowski10,
author = {Michael Piotrowski},
editor = {Apostolos Antonacopoulos and
Michael J. Gormish and
Rolf Ingold},
title = {Document conversion for cultural heritage texts: FrameMaker to {HTML}
revisited},
booktitle = {Proceedings of the 2010 {ACM} Symposium on Document Engineering, Manchester,
United Kingdom, September 21-24, 2010},
pages = {223--226},
publisher = {{ACM}},
year = {2010},
url = {https://doi.org/10.1145/1860559.1860608},
doi = {10.1145/1860559.1860608},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/doceng/Piotrowski10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/rjour/PauH09,
author = {Gr{\'{e}}goire Pau and
Wolfgang Huber},
title = {The hwriter package: Composing {HTML} documents with {R} objects},
journal = {R J.},
volume = {1},
number = {1},
pages = {22},
year = {2009},
url = {https://doi.org/10.32614/rj-2009-009},
doi = {10.32614/RJ-2009-009},
timestamp = {Tue, 27 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/rjour/PauH09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/compsystech/RozinajovaH09,
author = {Viera Rozinajov{\'{a}} and
Ondrej Hluch{\'{y}}},
editor = {Boris Rachev and
Angel Smrikarov},
title = {One approach to {HTML} wrappers creation: using Document Object Model
tree},
booktitle = {Proceedings of the 2009 International Conference on Computer Systems
and Technologies and Workshop for PhD Students in Computing, CompSysTech
2009, Rousse, Bulgaria, June 18-19, 2009},
pages = {41},
publisher = {{ACM}},
year = {2009},
url = {https://doi.org/10.1145/1731740.1731785},
doi = {10.1145/1731740.1731785},
timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/compsystech/RozinajovaH09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/coria/WaszakLB09,
author = {Thierry Waszak and
Claude de Loupy and
Patrice Bellot},
title = {Identification et structuration hi{\'{e}}rarchique des titres
dans les documents {HTML}},
booktitle = {COnf{\'{e}}rence en Recherche d'Infomations et Applications -
{CORIA} 2009, 6th French Information Retrieval Conference, Presqu'{\^{\i}}le
de Giens, France, May 5-7, 2009. Proceedings},
pages = {285--299},
publisher = {{LSIS-USTV}},
year = {2009},
url = {https://doi.org/10.24348/coria.2009.285},
doi = {10.24348/CORIA.2009.285},
timestamp = {Wed, 25 Sep 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/coria/WaszakLB09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hci/HenschenL09,
author = {Lawrence J. Henschen and
Julia C. Lee},
editor = {Constantine Stephanidis},
title = {Using Semantic-Level Tags in {HTML/XML} Documents},
booktitle = {Universal Access in Human-Computer Interaction. Applications and Services,
5th International Conference, {UAHCI} 2009, Held as Part of {HCI}
International 2009, San Diego, CA, USA, July 19-24, 2009. Proceedings,
Part {III}},
series = {Lecture Notes in Computer Science},
volume = {5616},
pages = {683--692},
publisher = {Springer},
year = {2009},
url = {https://doi.org/10.1007/978-3-642-02713-0\_72},
doi = {10.1007/978-3-642-02713-0\_72},
timestamp = {Tue, 14 May 2019 10:00:43 +0200},
biburl = {https://dblp.org/rec/conf/hci/HenschenL09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iih-msp/LeeC09b,
author = {Chin{-}Feng Lee and
Hsing{-}Ling Chen},
editor = {Jeng{-}Shyang Pan and
Yen{-}Wei Chen and
Lakhmi C. Jain},
title = {Data Concealment Scheme for {HTML} Documents Based on Color Code},
booktitle = {Fifth International Conference on Intelligent Information Hiding and
Multimedia Signal Processing {(IIH-MSP} 2009), Kyoto, Japan, 12-14
September, 2009, Proceedings},
pages = {632--635},
publisher = {{IEEE} Computer Society},
year = {2009},
url = {https://doi.org/10.1109/IIH-MSP.2009.19},
doi = {10.1109/IIH-MSP.2009.19},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/iih-msp/LeeC09b.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@phdthesis{DBLP:books/daglib/0022691,
author = {Thomas Gottron},
title = {Content extraction - identifying the main content in {HTML} documents},
school = {University of Mainz, Germany},
year = {2008},
url = {http://ubm.opus.hbz-nrw.de/volltexte/2009/1859/index.html},
urn = {urn:nbn:de:hebis:77-18591},
timestamp = {Sat, 17 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/books/daglib/0022691.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/cleiej/MenesesR08,
author = {Esteban Meneses and
Oldemar Rodr{\'{\i}}guez{-}Rojas},
title = {Measuring Contribution of {HTML} Features in Web Document Clustering},
journal = {{CLEI} Electron. J.},
volume = {11},
number = {2},
year = {2008},
url = {https://doi.org/10.19153/cleiej.11.2.7},
doi = {10.19153/CLEIEJ.11.2.7},
timestamp = {Tue, 21 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/cleiej/MenesesR08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tsmc/AshrafOA08,
author = {Fatima Ashraf and
Tansel {\"{O}}zyer and
Reda Alhajj},
title = {Employing Clustering Techniques for Automatic Information Extraction
From {HTML} Documents},
journal = {{IEEE} Trans. Syst. Man Cybern. Part {C}},
volume = {38},
number = {5},
pages = {660--673},
year = {2008},
url = {https://doi.org/10.1109/TSMCC.2008.923882},
doi = {10.1109/TSMCC.2008.923882},
timestamp = {Thu, 21 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tsmc/AshrafOA08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/IEEEscc/YangZT08,
author = {Stephen J. H. Yang and
Jia Zhang and
Stella T. C. Tsai},
title = {An Automatic Semantic Segment Detection Service for {HTML} Documents},
booktitle = {2008 {IEEE} International Conference on Services Computing {(SCC}
2008), 8-11 July 2008, Honolulu, Hawaii, {USA}},
pages = {210--217},
publisher = {{IEEE} Computer Society},
year = {2008},
url = {https://doi.org/10.1109/SCC.2008.155},
doi = {10.1109/SCC.2008.155},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/IEEEscc/YangZT08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iv/JernRAY08,
author = {Mikael Jern and
Jakob Rogstadius and
Tobias {\AA}str{\"{o}}m and
Anders Ynnerman},
title = {Visual Analytics Presentation Tools Applied in {HTML} Documents},
booktitle = {12th International Conference on Information Visualisation, {IV} 2008,
8-11 July 2008, London, {UK}},
pages = {200--207},
publisher = {{IEEE} Computer Society},
year = {2008},
url = {https://doi.org/10.1109/IV.2008.22},
doi = {10.1109/IV.2008.22},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/iv/JernRAY08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/cas/HaCohen-KernerSKF07,
author = {Yaakov HaCohen{-}Kerner and
Ittay Stern and
David Korkus and
Erick Fredj},
title = {Automatic Machine Learning of Keyphrase Extraction from Short Html
Documents Written in Hebrew},
journal = {Cybern. Syst.},
volume = {38},
number = {1},
pages = {1--21},
year = {2007},
url = {https://doi.org/10.1080/01969720600998546},
doi = {10.1080/01969720600998546},
timestamp = {Thu, 13 Aug 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/cas/HaCohen-KernerSKF07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/assets/KeysersRB07,
author = {Daniel Keysers and
Marius Renn and
Thomas M. Breuel},
editor = {Enrico Pontelli and
Shari Trewin},
title = {Improving accessibility of html documents bygenerating image-tags
in a proxy},
booktitle = {Proceedings of the 9th International {ACM} {SIGACCESS} Conference
on Computers and Accessibility, {ASSETS} 2007, Tempe, Arizona, USA,
October 15-17, 2007},
pages = {249--250},
publisher = {{ACM}},
year = {2007},
url = {https://doi.org/10.1145/1296843.1296896},
doi = {10.1145/1296843.1296896},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/assets/KeysersRB07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/doceng/WildeC07,
author = {Erik Wilde and
Philippe C. Cattin},
editor = {Peter R. King and
Steven J. Simske},
title = {Presenting in html},
booktitle = {Proceedings of the 2007 {ACM} Symposium on Document Engineering, Winnipeg,
Manitoba, Canada, August 28-31, 2007},
pages = {35--36},
publisher = {{ACM}},
year = {2007},
url = {https://doi.org/10.1145/1284420.1284432},
doi = {10.1145/1284420.1284432},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/doceng/WildeC07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/doceng/ZouLT07,
author = {Jie Zou and
Daniel X. Le and
George R. Thoma},
editor = {Peter R. King and
Steven J. Simske},
title = {Structure and content analysis for html medical articles: a hidden
markov model approach},
booktitle = {Proceedings of the 2007 {ACM} Symposium on Document Engineering, Winnipeg,
Manitoba, Canada, August 28-31, 2007},
pages = {199--201},
publisher = {{ACM}},
year = {2007},
url = {https://doi.org/10.1145/1284420.1284468},
doi = {10.1145/1284420.1284468},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/doceng/ZouLT07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/emnlp/KajiK07,
author = {Nobuhiro Kaji and
Masaru Kitsuregawa},
editor = {Jason Eisner},
title = {Building Lexicon for Sentiment Analysis from Massive Collection of
{HTML} Documents},
booktitle = {EMNLP-CoNLL 2007, Proceedings of the 2007 Joint Conference on Empirical
Methods in Natural Language Processing and Computational Natural Language
Learning, June 28-30, 2007, Prague, Czech Republic},
pages = {1075--1083},
publisher = {{ACL}},
year = {2007},
url = {https://aclanthology.org/D07-1115/},
timestamp = {Fri, 06 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/emnlp/KajiK07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/f-egc/WisniewskiG07,
author = {Guillaume Wisniewski and
Patrick Gallinari},
editor = {Monique Noirhomme{-}Fraiture and
Gilles Venturini},
title = {R{\'{e}}-ordonnancement pour l'apprentissage de transformations
de documents {HTML}},
booktitle = {Extraction et gestion des connaissances (EGC'2007), Actes des cinqui{\`{e}}mes
journ{\'{e}}es Extraction et Gestion des Connaissances, Namur,
Belgique, 23-26 janvier 2007, 2 Volumes},
series = {Revue des Nouvelles Technologies de l'Information},
volume = {{RNTI-E-9}},
pages = {727--738},
publisher = {C{\'{e}}padu{\`{e}}s-{\'{E}}ditions},
year = {2007},
url = {http://editions-rnti.fr/?inprocid=1001461},
timestamp = {Thu, 24 Apr 2014 17:37:27 +0200},
biburl = {https://dblp.org/rec/conf/f-egc/WisniewskiG07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icdar/Burget07,
author = {Radek Burget},
title = {Layout Based Information Extraction from {HTML} Documents},
booktitle = {9th International Conference on Document Analysis and Recognition
{(ICDAR} 2007), 23-26 September, Curitiba, Paran{\'{a}}, Brazil},
pages = {624--628},
publisher = {{IEEE} Computer Society},
year = {2007},
url = {https://doi.org/10.1109/ICDAR.2007.4376990},
doi = {10.1109/ICDAR.2007.4376990},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icdar/Burget07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/www/Alabi07,
author = {Kehinde Alabi},
editor = {Carey L. Williamson and
Mary Ellen Zurko and
Peter F. Patel{-}Schneider and
Prashant J. Shenoy},
title = {Generation, documentation and presentation of mathematical equations
and symbolic scientific expressions using pure {HTML} and {CSS}},
booktitle = {Proceedings of the 16th International Conference on World Wide Web,
{WWW} 2007, Banff, Alberta, Canada, May 8-12, 2007},
pages = {1321--1322},
publisher = {{ACM}},
year = {2007},
url = {https://doi.org/10.1145/1242572.1242830},
doi = {10.1145/1242572.1242830},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/www/Alabi07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/cn/SankaCC06,
author = {Anoop Sanka and
Shravan Chamakura and
Sharma Chakravarthy},
title = {A dataflow approach to efficient change detection of {HTML/XML} documents
in WebVigiL},
journal = {Comput. Networks},
volume = {50},
number = {10},
pages = {1547--1563},
year = {2006},
url = {https://doi.org/10.1016/j.comnet.2005.10.016},
doi = {10.1016/J.COMNET.2005.10.016},
timestamp = {Wed, 19 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/cn/SankaCC06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ACMicec/SimonLB06,
author = {Kai Simon and
Georg Lausen and
Harold Boley},
editor = {Mark S. Fox and
Bruce Spencer},
title = {From {HTML} documents to web tables and rules},
booktitle = {Proceedings of the 8th International Conference on Electronic Commerce:
The new e-commerce - Innovations for Conquering Current Barriers,
Obstacles and Limitations to Conducting Successful Business on the
Internet, 2006, Fredericton, New Brunswick, Canada, August 13-16,
2006},
series = {{ACM} International Conference Proceeding Series},
volume = {156},
pages = {125--131},
publisher = {{ACM}},
year = {2006},
url = {https://doi.org/10.1145/1151454.1151484},
doi = {10.1145/1151454.1151484},
timestamp = {Tue, 06 Apr 2021 12:12:56 +0200},
biburl = {https://dblp.org/rec/conf/ACMicec/SimonLB06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/acl/KajiK06,
author = {Nobuhiro Kaji and
Masaru Kitsuregawa},
editor = {Nicoletta Calzolari and
Claire Cardie and
Pierre Isabelle},
title = {Automatic Construction of Polarity-Tagged Corpus from {HTML} Documents},
booktitle = {{ACL} 2006, 21st International Conference on Computational Linguistics
and 44th Annual Meeting of the Association for Computational Linguistics,
Proceedings of the Conference, Sydney, Australia, 17-21 July 2006},
publisher = {The Association for Computer Linguistics},
year = {2006},
url = {https://aclanthology.org/P06-2059/},
timestamp = {Fri, 06 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/acl/KajiK06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/doceng/LeveringC06,
author = {Ryan Levering and
Michal Cutler},
editor = {Dick C. A. Bulterman and
David F. Brailsford},
title = {The portrait of a common {HTML} web page},
booktitle = {Proceedings of the 2006 {ACM} Symposium on Document Engineering, Amsterdam,
The Netherlands, October 10-13, 2006},
pages = {198--204},
publisher = {{ACM}},
year = {2006},
url = {https://doi.org/10.1145/1166160.1166213},
doi = {10.1145/1166160.1166213},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/doceng/LeveringC06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icdim/BhattiA06,
author = {Muhammad Afzal Bhatti and
Adeel Ahmad},
title = {{PDF} to {HTML} Conversion: Having a Usable Web Document},
booktitle = {First {IEEE} International Conference on Digital Information Management
(ICDIM), December 6-8, 2006, Christ College, Bangalore, India, Proceedings},
pages = {289--293},
publisher = {{IEEE}},
year = {2006},
url = {https://doi.org/10.1109/ICDIM.2007.369212},
doi = {10.1109/ICDIM.2007.369212},
timestamp = {Tue, 04 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icdim/BhattiA06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/www/NannoO06,
author = {Tomoyuki Nanno and
Manabu Okumura},
editor = {Les Carr and
David De Roure and
Arun Iyengar and
Carole A. Goble and
Michael Dahlin},
title = {{HTML2RSS:} automatic generation of {RSS} feed based on structure
analysis of {HTML} document},
booktitle = {Proceedings of the 15th international conference on World Wide Web,
{WWW} 2006, Edinburgh, Scotland, UK, May 23-26, 2006},
pages = {1061--1062},
publisher = {{ACM}},
year = {2006},
url = {https://doi.org/10.1145/1135777.1136015},
doi = {10.1145/1135777.1136015},
timestamp = {Wed, 14 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/www/NannoO06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/www/NannoO06a,
author = {Tomoyuki Nanno and
Manabu Okumura},
editor = {Les Carr and
David De Roure and
Arun Iyengar and
Carole A. Goble and
Michael Dahlin},
title = {{HTML2RSS:} automatic generation of {RSS} feed based on structure
analysis of {HTML} document},
booktitle = {Proceedings of the 15th international conference on World Wide Web,
{WWW} 2006, Edinburgh, Scotland, UK, May 23-26, 2006},
pages = {1075--1076},
publisher = {{ACM}},
year = {2006},
url = {https://doi.org/10.1145/1135777.1136022},
doi = {10.1145/1135777.1136022},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/www/NannoO06a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/NakanoTTIY05,
author = {Yuusuke Nakano and
Koji Tsukada and
Saeko Takagi and
Kei Iwasaki and
Fujiichi Yoshimoto},
title = {InCom: Support System for Informal Communication in 3D Virtual Worlds
Generated from {HTML} Documents},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {88-D},
number = {5},
pages = {872--879},
year = {2005},
url = {https://doi.org/10.1093/ietisy/e88-d.5.872},
doi = {10.1093/IETISY/E88-D.5.872},
timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieicet/NakanoTTIY05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jucs/Kolbitsch05,
author = {Josef Kolbitsch},
title = {Fine-Grained Transclusions of Multimedia Documents in {HTML}},
journal = {J. Univers. Comput. Sci.},
volume = {11},
number = {6},
pages = {926--943},
year = {2005},
url = {https://doi.org/10.3217/jucs-011-06-0926},
doi = {10.3217/JUCS-011-06-0926},
timestamp = {Thu, 07 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jucs/Kolbitsch05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ldvf/Rehm05,
author = {Georg Rehm},
title = {Language-Independent Text Parsing of Arbitrary HTML-Documents. Towards
{A} Foundation For Web Genre Identification},
journal = {{LDV} Forum},
volume = {20},
number = {2},
pages = {53--74},
year = {2005},
url = {http://www.jlcl.org/2005\_Heft2/Georg\_Rehm.pdf},
timestamp = {Mon, 19 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ldvf/Rehm05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/soco/PereiraMP05,
author = {Ricardo A. Marques Pereira and
Andrea Molinari and
Gabriella Pasi},
title = {Contextual weighted representations and indexing models for the retrieval
of {HTML} documents},
journal = {Soft Comput.},
volume = {9},
number = {7},
pages = {481--492},
year = {2005},
url = {https://doi.org/10.1007/s00500-004-0361-z},
doi = {10.1007/S00500-004-0361-Z},
timestamp = {Sat, 19 Oct 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/soco/PereiraMP05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/www/ChenM05,
author = {Huamin Chen and
Prasant Mohapatra},
title = {A Context-Aware {HTML/XML} Document Transmission Process for Mobile
Wireless Clients},
journal = {World Wide Web},
volume = {8},
number = {4},
pages = {439--461},
year = {2005},
url = {https://doi.org/10.1007/s11280-005-1314-x},
doi = {10.1007/S11280-005-1314-X},
timestamp = {Sat, 20 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/www/ChenM05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/www/GuptaKGCS05,
author = {Suhit Gupta and
Gail E. Kaiser and
Peter Grimm and
Michael F. Chiang and
Justin Starren},
title = {Automating Content Extraction of {HTML} Documents},
journal = {World Wide Web},
volume = {8},
number = {2},
pages = {179--224},
year = {2005},
url = {https://doi.org/10.1007/s11280-004-4873-3},
doi = {10.1007/S11280-004-4873-3},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/www/GuptaKGCS05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/amia/RoemerRF05,
author = {Lorrie K. Roemer and
Roberto A. Rocha and
Guilherme Del Fiol},
title = {Integration of {HTML} Documents into an XML-Based Knowledge Repository},
booktitle = {{AMIA} 2005, American Medical Informatics Association Annual Symposium,
Washington, DC, USA, October 22-26, 2005},
publisher = {{AMIA}},
year = {2005},
url = {https://knowledge.amia.org/amia-55142-a2005a-1.613296/t-003-1.615259/f-001-1.615260/a-394-1.615497/a-395-1.615494},
timestamp = {Wed, 17 Apr 2024 11:48:22 +0200},
biburl = {https://dblp.org/rec/conf/amia/RoemerRF05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/clihc/KirschningR05,
author = {Ingrid Kirschning and
Joaqu{\'{\i}}n O. Rueda},
editor = {Maria Cec{\'{\i}}lia Calani Baranauskas and
Oscar Mayora{-}Ibarra},
title = {Animated agents and {TTS} for {HTML} documents},
booktitle = {{CLIHC} '05, Proceedings of the 2005 Latin American Conference on
Human-Computer Interaction, Cuernavaca, Mexico, October 23-26, 2005},
pages = {148--154},
publisher = {{ACM}},
year = {2005},
url = {https://doi.org/10.1145/1111360.1111375},
doi = {10.1145/1111360.1111375},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/clihc/KirschningR05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/grc/YerraN05,
author = {Rajiv Yerra and
Yiu{-}Kai Ng},
editor = {Xiaohua Hu and
Qing Liu and
Andrzej Skowron and
Tsau Young Lin and
Ronald R. Yager and
Bo Zhang},
title = {Detecting similar {HTML} documents using a fuzzy set information retrieval
approach},
booktitle = {2005 {IEEE} International Conference on Granular Computing, Beijing,
China, July 25-27, 2005},
pages = {693--699},
publisher = {{IEEE}},
year = {2005},
url = {https://doi.org/10.1109/GRC.2005.1547380},
doi = {10.1109/GRC.2005.1547380},
timestamp = {Fri, 09 Apr 2021 17:11:12 +0200},
biburl = {https://dblp.org/rec/conf/grc/YerraN05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icde/MukherjeeRS05,
author = {Saikat Mukherjee and
I. V. Ramakrishnan and
Amarjeet Singh},
editor = {Karl Aberer and
Michael J. Franklin and
Shojiro Nishio},
title = {Bootstrapping Semantic Annotations for Content-Rich {HTML} Documents},
booktitle = {Proceedings of the 21st International Conference on Data Engineering,
{ICDE} 2005, 5-8 April 2005, Tokyo, Japan},
pages = {583--593},
publisher = {{IEEE} Computer Society},
year = {2005},
url = {https://doi.org/10.1109/ICDE.2005.28},
doi = {10.1109/ICDE.2005.28},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icde/MukherjeeRS05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ideas/LimN05,
author = {Seung Jin Lim and
Yiu{-}Kai Ng},
editor = {Bipin C. Desai and
Gottfried Vossen},
title = {Categorizing and Extracting Information from Multilingual {HTML} Documents},
booktitle = {Ninth International Database Engineering and Applications Symposium
{(IDEAS} 2005), 25-27 July 2005, Montreal, Canada},
pages = {415--422},
publisher = {{IEEE} Computer Society},
year = {2005},
url = {https://doi.org/10.1109/IDEAS.2005.15},
doi = {10.1109/IDEAS.2005.15},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ideas/LimN05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sigir/HuXSHSCL05,
author = {Yunhua Hu and
Guomao Xin and
Ruihua Song and
Guoping Hu and
Shuming Shi and
Yunbo Cao and
Hang Li},
editor = {Ricardo A. Baeza{-}Yates and
Nivio Ziviani and
Gary Marchionini and
Alistair Moffat and
John Tait},
title = {Title extraction from bodies of {HTML} documents and its application
to web page retrieval},
booktitle = {{SIGIR} 2005: Proceedings of the 28th Annual International {ACM} {SIGIR}
Conference on Research and Development in Information Retrieval, Salvador,
Brazil, August 15-19, 2005},
pages = {250--257},
publisher = {{ACM}},
year = {2005},
url = {https://doi.org/10.1145/1076034.1076079},
doi = {10.1145/1076034.1076079},
timestamp = {Wed, 02 Mar 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sigir/HuXSHSCL05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/www/KruplHG05,
author = {Bernhard Kr{\"{u}}pl and
Marcus Herzog and
Wolfgang Gatterbauer},
editor = {Allan Ellis and
Tatsuya Hagino},
title = {Using visual cues for extraction of tabular data from arbitrary {HTML}
documents},
booktitle = {Proceedings of the 14th international conference on World Wide Web,
{WWW} 2005, Chiba, Japan, May 10-14, 2005 - Special interest tracks
and posters},
pages = {1000--1001},
publisher = {{ACM}},
year = {2005},
url = {https://doi.org/10.1145/1062745.1062838},
doi = {10.1145/1062745.1062838},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/www/KruplHG05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/dn/DenoyerG04,
author = {Ludovic Denoyer and
Patrick Gallinari},
title = {Un mod{\`{e}}le de mixture de mod{\`{e}}les g{\'{e}}n{\'{e}}ratifs
pour les documents structur{\'{e}}s multim{\'{e}}dias. Application
{\`{a}} la classification de documents {XML} et {HTML}},
journal = {Document Num{\'{e}}rique},
volume = {8},
number = {3},
pages = {35--54},
year = {2004},
url = {http://dn.revuesonline.com/article.jsp?articleId=5188},
timestamp = {Sun, 24 Nov 2013 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/dn/DenoyerG04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijcpol/ZhangN04,
author = {Lihua Zhang and
Yiu{-}Kai Ng},
title = {A Query Engine for Retrieving Information from Chinese {HTML} Documents},
journal = {Int. J. Comput. Process. Orient. Lang.},
volume = {17},
number = {3},
pages = {135--164},
year = {2004},
url = {https://doi.org/10.1142/S0219427904001085},
doi = {10.1142/S0219427904001085},
timestamp = {Mon, 11 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ijcpol/ZhangN04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/dexaw/Burget04,
author = {Radek Burget},
title = {Hierarchies in {HTML} Documents: Linking Text to Concepts},
booktitle = {15th International Workshop on Database and Expert Systems Applications
{(DEXA} 2004), with CD-ROM, 30 August - 3 September 2004, Zaragoza,
Spain},
pages = {186--190},
publisher = {{IEEE} Computer Society},
year = {2004},
url = {https://doi.org/10.1109/DEXA.2004.1333471},
doi = {10.1109/DEXA.2004.1333471},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/dexaw/Burget04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iadis/BenoitN04,
author = {Beno{\^{\i}}t Encelle and
Nadine Baptiste{-}Jessel},
editor = {Pedro T. Isa{\'{\i}}as and
Nitya Karmakar and
Lu{\'{\i}}s E. T. Rodrigues and
Patr{\'{\i}}cia Barbosa},
title = {Using the concept of user policies for improving {HTML} documents
accessibility},
booktitle = {Proceedings of the {IADIS} International Conference WWW/Internet 2004,
Madrid, Spain, 2 Volumes},
pages = {835--839},
publisher = {{IADIS}},
year = {2004},
timestamp = {Wed, 01 Apr 2015 20:06:19 +0200},
biburl = {https://dblp.org/rec/conf/iadis/BenoitN04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iadis/SinkaC04,
author = {Mark P. Sinka and
David Corne},
editor = {Pedro T. Isa{\'{\i}}as and
Nitya Karmakar and
Lu{\'{\i}}s E. T. Rodrigues and
Patr{\'{\i}}cia Barbosa},
title = {Measuring Effectiveness of Text-Decorated {HTML} Tags in Web Document
Clustering},
booktitle = {Proceedings of the {IADIS} International Conference WWW/Internet 2004,
Madrid, Spain, 2 Volumes},
pages = {707--714},
publisher = {{IADIS}},
year = {2004},
timestamp = {Mon, 03 Jan 2005 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/iadis/SinkaC04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icchp/AnnamalaiGP04,
author = {Narayan Annamalai and
Gopal Gupta and
B. Prabhakaran},
editor = {Joachim Klaus and
Klaus Miesenberger and
Wolfgang L. Zagler and
Dominique Burger},
title = {Accessing Documents via Audio: An Extensible Transcoder for {HTML}
to VoiceXML Conversion},
booktitle = {Computers Helping People with Special Needs, 9th International Conference,
{ICCHP} 2004, Paris, France, July 7-9, 2004, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {3118},
pages = {339--346},
publisher = {Springer},
year = {2004},
url = {https://doi.org/10.1007/978-3-540-27817-7\_51},
doi = {10.1007/978-3-540-27817-7\_51},
timestamp = {Wed, 26 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icchp/AnnamalaiGP04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/saint/LimN04,
author = {Seung Jin Lim and
Yiu{-}Kai Ng},
title = {Change Discovery of Hierarchically Structured, Order-Sensitive Data
in {HTML/XML} Documents},
booktitle = {2004 Symposium on Applications and the Internet {(SAINT} 2004), 26-30
January 2004, Tokyo, Japan},
pages = {178--187},
publisher = {{IEEE} Computer Society},
year = {2004},
url = {https://doi.org/10.1109/SAINT.2004.1266114},
doi = {10.1109/SAINT.2004.1266114},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/saint/LimN04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/www/SankaCC04,
author = {Anoop Sanka and
Shravan Chamakura and
Sharma Chakravarthy},
editor = {Mark Levene and
Alexandra Poulovassilis},
title = {A Dataflow Approach To Efficient Change Detection of {HTML/XML} Documents
in WebVigiL},
booktitle = {Proceedings of the Third International Workshop on Web Dynamics, WebDyn@WWW
2004, New York, NY, USA, May 18, 2004},
series = {{CEUR} Workshop Proceedings},
volume = {703},
pages = {76--85},
publisher = {CEUR-WS.org},
year = {2004},
url = {https://ceur-ws.org/Vol-703/paper8.pdf},
timestamp = {Fri, 10 Mar 2023 16:22:22 +0100},
biburl = {https://dblp.org/rec/conf/www/SankaCC04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/apin/KimZ03,
author = {Sun Kim and
Byoung{-}Tak Zhang},
title = {Genetic Mining of {HTML} Structures for Effective Web-Document Retrieval},
journal = {Appl. Intell.},
volume = {18},
number = {3},
pages = {243--256},
year = {2003},
url = {https://doi.org/10.1023/A:1023293820057},
doi = {10.1023/A:1023293820057},
timestamp = {Wed, 17 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/apin/KimZ03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/bncod/PandrangiJSC03,
author = {Naveen Pandrangi and
Jyoti Jacob and
Anoop Sanka and
Sharma Chakravarthy},
editor = {Anne E. James and
Brian Lings and
Muhammad Younas},
title = {WebVigiL: User Profile-Based Change Detection for {HTML/XML} Documents},
booktitle = {New Horizons in Information Management, 20th British National Conference
on Databases, {BNCOD} 20, Coventry, UK, July 15-17, 2003, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {2712},
pages = {38--57},
publisher = {Springer},
year = {2003},
url = {https://doi.org/10.1007/3-540-45073-4\_5},
doi = {10.1007/3-540-45073-4\_5},
timestamp = {Tue, 14 May 2019 10:00:50 +0200},
biburl = {https://dblp.org/rec/conf/bncod/PandrangiJSC03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cmg/Wingfield03,
author = {Patricia E. Wingfield},
title = {No More Downloading - Using {SAS/ODS} to Create Graphs and {HTML}
Documents for {OS/390} Systems},
booktitle = {29th International Computer Measurement Group Conference, December
7-12, 2003, Dallas, Texas, USA, Proceedings},
pages = {469--475},
publisher = {Computer Measurement Group},
year = {2003},
url = {http://www.cmg.org/?s2member\_file\_download=/proceedings/2003/3189.pdf},
timestamp = {Wed, 17 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cmg/Wingfield03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ecir/CeciM03,
author = {Michelangelo Ceci and
Donato Malerba},
editor = {Fabrizio Sebastiani},
title = {Hierarchical Classification of {HTML} Documents with WebClassII},
booktitle = {Advances in Information Retrieval, 25th European Conference on {IR}
Research, {ECIR} 2003, Pisa, Italy, April 14-16, 2003, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {2633},
pages = {57--72},
publisher = {Springer},
year = {2003},
url = {https://doi.org/10.1007/3-540-36618-0\_5},
doi = {10.1007/3-540-36618-0\_5},
timestamp = {Tue, 14 May 2019 10:00:37 +0200},
biburl = {https://dblp.org/rec/conf/ecir/CeciM03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iadis/HyuseinP03,
author = {Byurhan Hyusein and
Ahmed Patel},
title = {Significance of {HTML} Tags for Document Indexing and Retrieval},
booktitle = {Proceedings of the {IADIS} International Conference WWW/Internet 2003,
{ICWI} 2003, Algarve, Portugal, November 5-8, 2003},
pages = {817--820},
publisher = {{IADIS}},
year = {2003},
timestamp = {Thu, 18 Mar 2004 15:27:46 +0100},
biburl = {https://dblp.org/rec/conf/iadis/HyuseinP03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icdar/MukherjeeYTR03,
author = {Saikat Mukherjee and
Guizhen Yang and
Wenfang Tan and
I. V. Ramakrishnan},
title = {Automatic Discovery of Semantic Structures in {HTML} Documents},
booktitle = {7th International Conference on Document Analysis and Recognition
{(ICDAR} 2003), 2-Volume Set, 3-6 August 2003, Edinburgh, Scotland,
{UK}},
pages = {245--249},
publisher = {{IEEE} Computer Society},
year = {2003},
url = {https://doi.org/10.1109/ICDAR.2003.1227667},
doi = {10.1109/ICDAR.2003.1227667},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icdar/MukherjeeYTR03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pakdd/YunLP03,
author = {Bo{-}Hyun Yun and
Myungeun Lim and
Soo{-}Hyun Park},
editor = {Kyu{-}Young Whang and
Jongwoo Jeon and
Kyuseok Shim and
Jaideep Srivastava},
title = {An Integrated System of Mining {HTML} Texts and Filtering Structured
Documents},
booktitle = {Advances in Knowledge Discovery and Data Mining, 7th Pacific-Asia
Conference, {PAKDD} 2003, Seoul, Korea, April 30 - May 2, 2003, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {2637},
pages = {350--355},
publisher = {Springer},
year = {2003},
url = {https://doi.org/10.1007/3-540-36175-8\_34},
doi = {10.1007/3-540-36175-8\_34},
timestamp = {Tue, 14 May 2019 10:00:51 +0200},
biburl = {https://dblp.org/rec/conf/pakdd/YunLP03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pris/KerlochPG03,
author = {Fr{\'{e}}d{\'{e}}ric Kerloch and
Thierry Paquet and
Patrick Gallinari},
editor = {Jean{-}Marc Ogier and
{\'{E}}ric Trupin},
title = {Using Structure For Information Extraction In Html Documents},
booktitle = {Pattern Recognition in Information Systems, Proceedings of the 3rd
International Workshop on Pattern Recognition in Information Systems,
{PRIS} 2003, In conjunction with {ICEIS} 2003, Angers, France, April
2003},
pages = {173--178},
publisher = {{ICEIS} Press},
year = {2003},
timestamp = {Mon, 01 Sep 2003 14:36:20 +0200},
biburl = {https://dblp.org/rec/conf/pris/KerlochPG03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sac/MolinariPP03,
author = {Andrea Molinari and
Ricardo A. Marques Pereira and
Gabriella Pasi},
editor = {Gary B. Lamont and
Hisham Haddad and
George A. Papadopoulos and
Brajendra Panda},
title = {An Indexing Model of {HTML} Documents},
booktitle = {Proceedings of the 2003 {ACM} Symposium on Applied Computing (SAC),
March 9-12, 2003, Melbourne, FL, {USA}},
pages = {834--840},
publisher = {{ACM}},
year = {2003},
url = {https://doi.org/10.1145/952532.952697},
doi = {10.1145/952532.952697},
timestamp = {Tue, 06 Nov 2018 11:06:45 +0100},
biburl = {https://dblp.org/rec/conf/sac/MolinariPP03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/semweb/MukherjeeYR03,
author = {Saikat Mukherjee and
Guizhen Yang and
I. V. Ramakrishnan},
editor = {Dieter Fensel and
Katia P. Sycara and
John Mylopoulos},
title = {Automatic Annotation of Content-Rich {HTML} Documents: Structural
and Semantic Analysis},
booktitle = {The Semantic Web - {ISWC} 2003, Second International Semantic Web
Conference, Sanibel Island, FL, USA, October 20-23, 2003, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {2870},
pages = {533--549},
publisher = {Springer},
year = {2003},
url = {https://doi.org/10.1007/978-3-540-39718-2\_34},
doi = {10.1007/978-3-540-39718-2\_34},
timestamp = {Tue, 07 Sep 2021 13:48:16 +0200},
biburl = {https://dblp.org/rec/conf/semweb/MukherjeeYR03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/wirn/PilatoVVCS03,
author = {Giovanni Pilato and
Salvatore Vitabile and
Giorgio Vassallo and
Vincenzo Conti and
Filippo Sorbello},
editor = {Bruno Apolloni and
Maria Marinaro and
Roberto Tagliaferri},
title = {A Concurrent Neural Classifier for {HTML} Documents Retrieval},
booktitle = {Neural Nets, 14th Italian Workshop on Neural Nets, {WIRN} {VIETRI}
2003, Vietri sul Mare, Italy, June 4-7, 2003, Revised Papers},
series = {Lecture Notes in Computer Science},
volume = {2859},
pages = {210--217},
publisher = {Springer},
year = {2003},
url = {https://doi.org/10.1007/978-3-540-45216-4\_24},
doi = {10.1007/978-3-540-45216-4\_24},
timestamp = {Sun, 02 Jun 2019 21:17:04 +0200},
biburl = {https://dblp.org/rec/conf/wirn/PilatoVVCS03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/www/GuptaKNG03,
author = {Suhit Gupta and
Gail E. Kaiser and
David Neistadt and
Peter Grimm},
editor = {Guszt{\'{a}}v Hencsey and
Bebo White and
Yih{-}Farn Robin Chen and
L{\'{a}}szl{\'{o}} Kov{\'{a}}cs and
Steve Lawrence},
title = {DOM-based content extraction of {HTML} documents},
booktitle = {Proceedings of the Twelfth International World Wide Web Conference,
{WWW} 2003, Budapest, Hungary, May 20-24, 2003},
pages = {207--214},
publisher = {{ACM}},
year = {2003},
url = {https://doi.org/10.1145/775152.775182},
doi = {10.1145/775152.775182},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/www/GuptaKNG03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/www/KellyJP03,
author = {Brian Kelly and
Pete Johnston and
Andy Powell},
editor = {Irwin King and
Tam{\'{a}}s M{\'{a}}ray},
title = {Approaches to Validation of Dublin Core Metadata Embedded in {(X)HTML}
Documents},
booktitle = {Proceedings of the Twelfth International World Wide Web Conference
- Posters, {WWW} 2003, Budapest, Hungary, May 20-24, 2003},
year = {2003},
url = {http://www2003.org/cdrom/papers/poster/p109/p109-kelly.html},
timestamp = {Wed, 17 Jul 2013 16:59:51 +0200},
biburl = {https://dblp.org/rec/conf/www/KellyJP03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@incollection{DBLP:books/ws/03/0001H03,
author = {Yalin Wang and
Jianying Hu},
editor = {Apostolos Antonacopoulos and
Jianying Hu},
title = {Automatic Table Detection in {HTML} Documents},
booktitle = {Web Document Analysis},
series = {Series in Machine Perception and Artificial Intelligence},
volume = {55},
pages = {135--154},
publisher = {World Scientific},
year = {2003},
url = {https://doi.org/10.1142/9789812775375\_0008},
doi = {10.1142/9789812775375\_0008},
timestamp = {Mon, 26 Aug 2019 18:32:49 +0200},
biburl = {https://dblp.org/rec/books/ws/03/0001H03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@incollection{DBLP:books/ws/03/AlamHR03,
author = {Hassan Alam and
Rachmat Hartono and
A. F. R. Rahman},
editor = {Apostolos Antonacopoulos and
Jianying Hu},
title = {Extraction and Management of Content from {HTML} Documents},
booktitle = {Web Document Analysis},
series = {Series in Machine Perception and Artificial Intelligence},
volume = {55},
pages = {95--111},
publisher = {World Scientific},
year = {2003},
url = {https://doi.org/10.1142/9789812775375\_0006},
doi = {10.1142/9789812775375\_0006},
timestamp = {Mon, 26 Aug 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/books/ws/03/AlamHR03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@incollection{DBLP:books/ws/03/YangCZ03,
author = {Yudong Yang and
Yu Chen and
HongJiang Zhang},
editor = {Apostolos Antonacopoulos and
Jianying Hu},
title = {Html Page Analysis based on Visual cues},
booktitle = {Web Document Analysis},
series = {Series in Machine Perception and Artificial Intelligence},
volume = {55},
pages = {113--131},
publisher = {World Scientific},
year = {2003},
url = {https://doi.org/10.1142/9789812775375\_0007},
doi = {10.1142/9789812775375\_0007},
timestamp = {Mon, 26 Aug 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/books/ws/03/YangCZ03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jfp/Thiemann02,
author = {Peter Thiemann},
title = {A typed representation for {HTML} and {XML} documents in Haskell},
journal = {J. Funct. Program.},
volume = {12},
number = {4{\&}5},
pages = {435--468},
year = {2002},
url = {https://doi.org/10.1017/S0956796802004392},
doi = {10.1017/S0956796802004392},
timestamp = {Mon, 23 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/jfp/Thiemann02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/das/WangH02,
author = {Yalin Wang and
Jianying Hu},
editor = {Daniel P. Lopresti and
Jianying Hu and
Ramanujan S. Kashi},
title = {Detecting Tables in {HTML} Documents},
booktitle = {Document Analysis Systems V, 5th International Workshop, {DAS} 2002,
Princeton, NJ, USA, August 19-21, 2002, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {2423},
pages = {249--260},
publisher = {Springer},
year = {2002},
url = {https://doi.org/10.1007/3-540-45869-7\_29},
doi = {10.1007/3-540-45869-7\_29},
timestamp = {Wed, 16 Mar 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/das/WangH02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/dexa/Liu02,
author = {Mengchi Liu},
editor = {Abdelkader Hameurlain and
Rosine Cicchetti and
Roland Traunm{\"{u}}ller},
title = {Capturing Semantics in {HTML} Documents},
booktitle = {Database and Expert Systems Applications, 13th International Conference,
{DEXA} 2002, Aix-en-Provence, France, September 2-6, 2002, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {2453},
pages = {103--112},
publisher = {Springer},
year = {2002},
url = {https://doi.org/10.1007/3-540-46146-9\_11},
doi = {10.1007/3-540-46146-9\_11},
timestamp = {Tue, 14 May 2019 10:00:46 +0200},
biburl = {https://dblp.org/rec/conf/dexa/Liu02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/edbtw/MalerbaEC02,
author = {Donato Malerba and
Floriana Esposito and
Michelangelo Ceci},
editor = {Akmal B. Chaudhri and
Rainer Unland and
Chabane Djeraba and
Wolfgang Lindner},
title = {Mining {HTML} Pages to Support Document Sharing in a Cooperative System},
booktitle = {XML-Based Data Management and Multimedia Engineering - {EDBT} 2002
Workshops, {EDBT} 2002 Workshops XMLDM, MDDE, and YRWS, Prague, Czech
Republic, March 24-28, 2002, Revised Papers},
series = {Lecture Notes in Computer Science},
volume = {2490},
pages = {420--434},
publisher = {Springer},
year = {2002},
url = {https://doi.org/10.1007/3-540-36128-6\_25},
doi = {10.1007/3-540-36128-6\_25},
timestamp = {Tue, 14 May 2019 10:00:54 +0200},
biburl = {https://dblp.org/rec/conf/edbtw/MalerbaEC02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iadis/HashemiFVT02,
author = {Ray R. Hashemi and
Charles Wesley Ford and
Tim Vamprooyen and
John R. Talburt},
title = {Extraction of Features with Unstructured Representation from {HTML}
Documents},
booktitle = {Proceedings of the {IADIS} International Conference WWW/Internet 2002,
{ICWI} 2002, Lisbon, Portugal, November 13-15, 2002},
pages = {47--53},
publisher = {{IADIS}},
year = {2002},
timestamp = {Thu, 30 Jun 2005 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iadis/HashemiFVT02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ideal/UmeharaIN02,
author = {Masayuki Umehara and
Koji Iwanuma and
Hidetomo Nabeshima},
editor = {Hujun Yin and
Nigel M. Allinson and
Richard T. Freeman and
John A. Keane and
Simon J. Hubbard},
title = {A Case-Based Recognition of Semantic Structures in {HTML} Documents},
booktitle = {Intelligent Data Engineering and Automated Learning - {IDEAL} 2002,
Third International Conference, Manchester, UK, August 12-14, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {2412},
pages = {141--147},
publisher = {Springer},
year = {2002},
url = {https://doi.org/10.1007/3-540-45675-9\_24},
doi = {10.1007/3-540-45675-9\_24},
timestamp = {Tue, 14 May 2019 10:00:45 +0200},
biburl = {https://dblp.org/rec/conf/ideal/UmeharaIN02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/www/CohenHJ02,
author = {William W. Cohen and
Matthew Hurst and
Lee S. Jensen},
editor = {David Lassner and
David De Roure and
Arun Iyengar},
title = {A flexible learning system for wrapping tables and lists in {HTML}
documents},
booktitle = {Proceedings of the Eleventh International World Wide Web Conference,
{WWW} 2002, May 7-11, 2002, Honolulu, Hawaii, {USA}},
pages = {232--241},
publisher = {{ACM}},
year = {2002},
url = {https://doi.org/10.1145/511446.511477},
doi = {10.1145/511446.511477},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/www/CohenHJ02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/amia/DubeyC01,
author = {Anil K. Dubey and
Henry C. Chueh},
title = {Using {XML} Metadata to Enable the Automatic Generation and Processing
of {HTML} Forms from {XML} Documents},
booktitle = {{AMIA} 2001, American Medical Informatics Association Annual Symposium,
Washington, DC, USA, November 3-7, 2001},
publisher = {{AMIA}},
year = {2001},
url = {https://knowledge.amia.org/amia-55142-a2001a-1.597057/t-002-1.598852/f-001-1.598853/a-251-1.599384/a-252-1.599381},
timestamp = {Wed, 17 Apr 2024 11:48:39 +0200},
biburl = {https://dblp.org/rec/conf/amia/DubeyC01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/flairs/SakamotoMAA01,
author = {Hiroshi Sakamoto and
Yoshitsugu Murakami and
Hiroki Arimura and
Setsuo Arikawa},
editor = {Ingrid Russell and
John F. Kolen},
title = {Extracting Partial Structures from {HTML} Documents},
booktitle = {Proceedings of the Fourteenth International Florida Artificial Intelligence
Research Society Conference, May 21-23, 2001, Key West, Florida, {USA}},
pages = {264--268},
publisher = {{AAAI} Press},
year = {2001},
url = {http://www.aaai.org/Library/FLAIRS/2001/flairs01-051.php},
timestamp = {Wed, 26 Oct 2022 08:35:34 +0200},
biburl = {https://dblp.org/rec/conf/flairs/SakamotoMAA01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icdar/DiligentiGMS01,
author = {Michelangelo Diligenti and
Marco Gori and
Marco Maggini and
Franco Scarselli},
title = {Classification of {HTML} Documents by Hidden Tree-Markov Models},
booktitle = {6th International Conference on Document Analysis and Recognition
{(ICDAR} 2001), 10-13 September 2001, Seattle, WA, {USA}},
pages = {849--853},
publisher = {{IEEE} Computer Society},
year = {2001},
url = {https://doi.org/10.1109/ICDAR.2001.953907},
doi = {10.1109/ICDAR.2001.953907},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icdar/DiligentiGMS01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icde/LimN01,
author = {Seung Jin Lim and
Yiu{-}Kai Ng},
editor = {Dimitrios Georgakopoulos and
Alexander Buchmann},
title = {An Automated Change Detection Algorithm for {HTML} Documents Based
on Semantic Hierarchies},
booktitle = {Proceedings of the 17th International Conference on Data Engineering,
April 2-6, 2001, Heidelberg, Germany},
pages = {303--312},
publisher = {{IEEE} Computer Society},
year = {2001},
url = {https://doi.org/10.1109/ICDE.2001.914842},
doi = {10.1109/ICDE.2001.914842},
timestamp = {Fri, 15 Mar 2024 12:30:44 +0100},
biburl = {https://dblp.org/rec/conf/icde/LimN01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/widm/Rapela01,
author = {Joaquin Rapela},
editor = {Roger H. L. Chiang and
Ee{-}Peng Lim},
title = {Automatically combining ranking heuristics for {HTML} documents},
booktitle = {3rd International Workshop on Web Information and Data Management
{(WIDM} 2001), Friday, 9 November 2001, In Conjunction with {ACM}
{CIKM} 2001, Doubletree Hotel Atlanta-Buckhead, Atlanta, Georgia,
{USA.} ACM, 2001},
pages = {61--67},
publisher = {{ACM}},
year = {2001},
url = {https://doi.org/10.1145/502932.502945},
doi = {10.1145/502932.502945},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/widm/Rapela01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/woa/GarelliF01,
author = {Francesco Garelli and
Carlo Ferrari},
editor = {Andrea Omicini and
Mirko Viroli},
title = {Object Oriented Mapping for {HTML} Documents},
booktitle = {{WOA} 2001: Dagli Oggetti agli Agenti. 2nd AI*IA/TABOO Joint Workshop
"From Objects to Agents": Evolutive Trends of Software Systems, 4-5
September 2001, Modena, Italy},
pages = {68--73},
publisher = {Pitagora Editrice Bologna},
year = {2001},
timestamp = {Mon, 17 Jan 2005 15:56:23 +0100},
biburl = {https://dblp.org/rec/conf/woa/GarelliF01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cl/LimN00,
author = {Seung Jin Lim and
Yiu{-}Kai Ng},
editor = {John W. Lloyd and
Ver{\'{o}}nica Dahl and
Ulrich Furbach and
Manfred Kerber and
Kung{-}Kiu Lau and
Catuscia Palamidessi and
Lu{\'{\i}}s Moniz Pereira and
Yehoshua Sagiv and
Peter J. Stuckey},
title = {A Heuristic Approach for Converting {HTML} Documents to {XML} Documents},
booktitle = {Computational Logic - {CL} 2000, First International Conference, London,
UK, 24-28 July, 2000, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {1861},
pages = {1182--1196},
publisher = {Springer},
year = {2000},
url = {https://doi.org/10.1007/3-540-44957-4\_79},
doi = {10.1007/3-540-44957-4\_79},
timestamp = {Tue, 14 May 2019 10:00:42 +0200},
biburl = {https://dblp.org/rec/conf/cl/LimN00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ecis/MotheRRZ00,
author = {Josiane Mothe and
Franck Ravat and
Farshad Riahi and
Gilles Zurfluh},
editor = {Hans Robert Hansen and
Martin Bichler and
Harald Mahrer},
title = {Structuration and Enrichment of {HTML} Documents in order to Build
a Specific Information Warehouse},
booktitle = {Proceedings of the 8th European Conference on Information Systems,
Trends in Information and Communication Systems for the 21st Century,
{ECIS} 2000, Vienna, Austria, July 3-5, 2000},
pages = {386--395},
year = {2000},
url = {http://aisel.aisnet.org/ecis2000/112},
timestamp = {Mon, 05 Dec 2016 15:14:00 +0100},
biburl = {https://dblp.org/rec/conf/ecis/MotheRRZ00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icmcs/FerriGGP00,
author = {Fernando Ferri and
Cristina Ghiselli and
Patrizia Grifoni and
Marco Padula},
title = {Toward a Retrieval of {HTML} Documents using a Semantic Approach},
booktitle = {2000 {IEEE} International Conference on Multimedia and Expo, {ICME}
2000, New York, NY, USA, July 30 - August 2, 2000},
pages = {1571--1574},
publisher = {{IEEE} Computer Society},
year = {2000},
url = {https://doi.org/10.1109/ICME.2000.871069},
doi = {10.1109/ICME.2000.871069},
timestamp = {Mon, 09 Aug 2021 14:54:02 +0200},
biburl = {https://dblp.org/rec/conf/icmcs/FerriGGP00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pricai/KimZ00,
author = {Sun Kim and
Byoung{-}Tak Zhang},
editor = {Ah{-}Hwee Tan and
Philip S. Yu},
title = {Web-Document Retrieval by Genetic Learning of Importance Factors for
{HTML} Tags},
booktitle = {Proceedings of the International Workshop on Text and Web Mining,
Melbourne, Australia, August 2000},
pages = {13--23},
year = {2000},
url = {http://textmining.krdl.org.sg/PRICAI2000/web-retrieval.pdf},
timestamp = {Wed, 27 Jun 2018 13:48:41 +0200},
biburl = {https://dblp.org/rec/conf/pricai/KimZ00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sigdoc/Green00b,
author = {Robin Green},
editor = {Susan B. Jones and
Beth Weise Moeller and
Michael Priestley and
Bernadette Longo},
title = {Documentation meets version control: an automated backup system for
HTML-based help},
booktitle = {Proceedings of {IEEE} Professional Communication Society International
Professional Communication Conference and Proceedings of the 18th
Annual {ACM} International Conference on Computer Documentation: Technology
{\&} Teamwork, Cambridge, Massachusetts, USA, September 24-27,
2000},
pages = {541--548},
publisher = {{IEEE}},
year = {2000},
url = {https://dl.acm.org/citation.cfm?id=504878},
timestamp = {Tue, 27 Nov 2018 10:40:38 +0100},
biburl = {https://dblp.org/rec/conf/sigdoc/Green00b.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jilt/Morrison99,
author = {Alex Morrison},
title = {Hijack on the road to Xanadu: The Infringement of Copyright in {HTML}
Documents via Networked Computers and the Legitimacy of Browsing Hypermedia
Documents},
journal = {J. Inf. Law Technol.},
volume = {1999},
number = {1},
year = {1999},
url = {http://elj.warwick.ac.uk/jilt/99-1/morrison.html},
timestamp = {Wed, 31 Mar 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jilt/Morrison99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/adbis/Polcicova99,
author = {Gabriela Polcicov{\'{a}}},
editor = {Johann Eder and
Ivan Rozman and
Tatjana Welzer},
title = {Recommending HTML-documents using Features Guided Automated Collaborative
Filtering},
booktitle = {Advances in Databases and Information Systems, Third East European
Conference, ADBIS'99, Maribor, Slovenia, September 13-16, 1999, Proceedings
of Short Papers},
pages = {81--87},
publisher = {Institute of Informatics, Faculty of Electrical Engineering and Computer
Science, Smetanova 17, {IS-2000} Maribor, Slovenia},
year = {1999},
timestamp = {Tue, 02 Nov 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/adbis/Polcicova99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/dasfaa/LimN99,
author = {Seung Jin Lim and
Yiu{-}Kai Ng},
editor = {Arbee L. P. Chen and
Frederick H. Lochovsky},
title = {WebView: {A} Tool for Retrieving Internal Structures and Extracting
Information from {HTML} Documents},
booktitle = {Database Systems for Advanced Applications, Proceedings of the Sixth
International Conference on Database Systems for Advanced Applications
(DASFAA), April 19-21, Hsinchu, Taiwan},
pages = {71--80},
publisher = {{IEEE} Computer Society},
year = {1999},
url = {https://doi.org/10.1109/DASFAA.1999.765738},
doi = {10.1109/DASFAA.1999.765738},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/dasfaa/LimN99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icai/KwakKL99,
author = {Ju{-}hyun Kwak and
Keecheon Kim and
Chang{-}Hoon Lee},
editor = {Hamid R. Arabnia},
title = {Advanced User Profile Agent Using Structure Analysis of {HTML} Document},
booktitle = {Proceedings of the International Conference on Artificial Intelligence,
{IC-AI} '99, June 28 - July 1, 1999, Las Vegas, Nevada, USA, Volume
1},
pages = {319--323},
publisher = {{CSREA} Press},
year = {1999},
timestamp = {Fri, 18 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icai/KwakKL99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/imsa/PacificiY99,
author = {Giovanni Pacifici and
Alaa Youssef},
editor = {Borko Furht},
title = {Synchronous Annotation of Shared {HTML} Documents},
booktitle = {Internet, Multimedia Systems and Applications, {IMSA} 1999, October
18-21, 1999, Nassau, The Bahamas},
pages = {275--279},
publisher = {{IASTED/ACTA} Press},
year = {1999},
timestamp = {Sun, 28 Jul 2019 13:40:03 +0200},
biburl = {https://dblp.org/rec/conf/imsa/PacificiY99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interact/FarhatB99,
author = {Siwar Farhat and
Yacine Bellik},
editor = {M. Angela Sasse and
Chris W. Johnson},
title = {SeeWeb: Dynamic Improvement of the Accessibility of {HTML} Documents
for Blind Persons},
booktitle = {Human-Computer Interaction {INTERACT} '99: {IFIP} {TC13} International
Conference on Human-Computer Interaction, Edinburgh, UK, 30th August-3rd
September 1999},
pages = {256--262},
publisher = {{IOS} Press},
year = {1999},
timestamp = {Mon, 19 Sep 2016 17:00:14 +0200},
biburl = {https://dblp.org/rec/conf/interact/FarhatB99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sigdoc/AhrensL99,
author = {Virginie Ahrens and
Val{\'{e}}rie Lecompte},
editor = {Johndan Johnson{-}Eilola and
Stuart A. Selber},
title = {Paper to {HTML} - an automatic, seamless process for documentation
production},
booktitle = {Proceedings of the 17th annual international conference on Documentation,
{SIGDOC} 1999, New Orleans, Louisiana, USA, September 12-14, 1999},
pages = {138--143},
publisher = {{ACM}},
year = {1999},
url = {https://doi.org/10.1145/318372.318571},
doi = {10.1145/318372.318571},
timestamp = {Tue, 06 Nov 2018 11:07:46 +0100},
biburl = {https://dblp.org/rec/conf/sigdoc/AhrensL99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/webdb/SahuguetA99,
author = {Arnaud Sahuguet and
Fabien Azavant},
editor = {Sophie Cluet and
Tova Milo},
title = {Web Ecology: Recycling {HTML} Pages as {XML} Documents Using {W4F}},
booktitle = {{ACM} {SIGMOD} Workshop on The Web and Databases, WebDB 1999, Philadelphia,
Pennsylvania, USA, June 3-4, 1999. Informal Proceedings},
pages = {31--36},
publisher = {{INRIA}},
year = {1999},
url = {http://www-rocq.inria.fr/\&\#126;cluet/WEBDB/sahuguet.ps},
timestamp = {Wed, 08 Feb 2017 16:53:29 +0100},
biburl = {https://dblp.org/rec/conf/webdb/SahuguetA99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/rfc/rfc2557,
author = {Jacob Palme and
Alex Hopmann and
Nick Shelness},
title = {{MIME} Encapsulation of Aggregate Documents, such as {HTML} {(MHTML)}},
journal = {{RFC}},
volume = {2557},
pages = {1--28},
year = {1999},
url = {https://doi.org/10.17487/RFC2557},
doi = {10.17487/RFC2557},
timestamp = {Tue, 14 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/rfc/rfc2557.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/criwg/RuizF98,
author = {D. C. Ruiz and
Jes{\'{u}}s Favela},
title = {Collaborative Review and Edition of {HTML} Documents},
booktitle = {{CRIWG} '98, Fourth International Workshop on Groupware, B{\'{u}}zios,
Rio de Janeiro, Brazil, September 9-11, 1998, Proceedings},
pages = {113--127},
year = {1998},
timestamp = {Thu, 24 Mar 2016 12:03:44 +0100},
biburl = {https://dblp.org/rec/conf/criwg/RuizF98.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ercimdl/SugimotoMDONT98,
author = {Shigeo Sugimoto and
Akira Maeda and
Myriam Dartois and
Jun Ohta and
Shigetaka Nakao and
Tetsuo Sakaguchi and
Koichi Tabata},
editor = {Christos Nikolaou and
Constantine Stephanidis},
title = {Experimental Studies on an Applet-based Document Viewer for Multilingual
{WWW} Documents - Functional Extension of and Lessons Learned from
Multilingual {HTML}},
booktitle = {Research and Advanced Technology for Digital Libraries, Second European
Conference, {ECDL} '98, Heraklion, Crete, Greece, September 21-23,
1998, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {1513},
pages = {199--214},
publisher = {Springer},
year = {1998},
url = {https://doi.org/10.1007/3-540-49653-X\_13},
doi = {10.1007/3-540-49653-X\_13},
timestamp = {Mon, 28 Aug 2023 21:17:44 +0200},
biburl = {https://dblp.org/rec/conf/ercimdl/SugimotoMDONT98.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/fodo/LimN98,
author = {Seung Jin Lim and
Yiu{-}Kai Ng},
editor = {Katsumi Tanaka and
Shahram Ghandeharizadeh},
title = {Constructing Hierarchical Information Structures of Sub-Page Level
{HTML} Documents},
booktitle = {The 5th International Conference of Foundations of Data Organization
(FODO'98), Kobe, Japan, November 12-13, 1998},
pages = {66--75},
year = {1998},
timestamp = {Tue, 27 Jul 2004 12:53:36 +0200},
biburl = {https://dblp.org/rec/conf/fodo/LimN98.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/zum/CiancariniMV98,
author = {Paolo Ciancarini and
Cecilia Mascolo and
Fabio Vitali},
editor = {Jonathan P. Bowen and
Andreas Fett and
Michael G. Hinchey},
title = {Visualizing {Z} Notation in {HTML} Documents},
booktitle = {{ZUM} '98: The {Z} Formal Specification Notation, 11th International
Conference of {Z} Users, Berlin, Germany, September 24-26, 1998, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {1493},
pages = {81--95},
publisher = {Springer},
year = {1998},
url = {https://doi.org/10.1007/978-3-540-49676-2\_7},
doi = {10.1007/978-3-540-49676-2\_7},
timestamp = {Tue, 14 May 2019 10:00:53 +0200},
biburl = {https://dblp.org/rec/conf/zum/CiancariniMV98.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/HsuY97,
author = {Jane Yung{-}jen Hsu and
Wen{-}tau Yih},
editor = {Benjamin Kuipers and
Bonnie L. Webber},
title = {Template-Based Information Mining from {HTML} Documents},
booktitle = {Proceedings of the Fourteenth National Conference on Artificial Intelligence
and Ninth Innovative Applications of Artificial Intelligence Conference,
{AAAI} 97, {IAAI} 97, July 27-31, 1997, Providence, Rhode Island,
{USA}},
pages = {256--262},
publisher = {{AAAI} Press / The {MIT} Press},
year = {1997},
url = {http://www.aaai.org/Library/AAAI/1997/aaai97-040.php},
timestamp = {Tue, 05 Sep 2023 08:53:09 +0200},
biburl = {https://dblp.org/rec/conf/aaai/HsuY97.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/bsdia/Tayeb-beyS97,
author = {Souad Tayeb{-}bey and
Alexander S. Saidi},
editor = {Nabeel A. Murshed and
Fl{\'{a}}vio Bortolozzi},
title = {Grammatical Formalism for Document Understanding System: From Documents
towards {HTML} Text},
booktitle = {Advances in Document Image Analysis, First Brazilian Symposium, BSDIA'97,
Curitiba, Brazil, November 2-5, 1997, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {1339},
pages = {165--175},
publisher = {Springer},
year = {1997},
url = {https://doi.org/10.1007/3-540-63791-5\_12},
doi = {10.1007/3-540-63791-5\_12},
timestamp = {Tue, 14 May 2019 10:00:53 +0200},
biburl = {https://dblp.org/rec/conf/bsdia/Tayeb-beyS97.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icdar/HongS97,
author = {Tao Hong and
Sargur N. Srihari},
title = {Representing OCRed documents in {HTML}},
booktitle = {4th International Conference Document Analysis and Recognition {(ICDAR}
'97), 2-Volume Set, August 18-20, 1997, Ulm, Germany, Proceedings},
pages = {831--835},
publisher = {{IEEE} Computer Society},
year = {1997},
url = {https://doi.org/10.1109/ICDAR.1997.620628},
doi = {10.1109/ICDAR.1997.620628},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icdar/HongS97.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sigdoc/Priestley97,
author = {Michael Priestley},
editor = {Karl L. Smart},
title = {Navigation Issues in Hypertext: Documenting Complex Hierarchies with
{HTML} Frames},
booktitle = {The 15th Annual International Conference of Computer Documentation:
Crossroads in Communication, {SIGDOC} 1997, Salt Lake City, Utah,
USA, October 19-22, 1997},
pages = {223--235},
publisher = {{ACM}},
year = {1997},
url = {https://doi.org/10.1145/263367.263396},
doi = {10.1145/263367.263396},
timestamp = {Tue, 06 Nov 2018 11:07:46 +0100},
biburl = {https://dblp.org/rec/conf/sigdoc/Priestley97.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/usits/CutlerSM97,
author = {Michal Cutler and
Yungming Shih and
Weiyi Meng},
title = {Using the Structure of {HTML} Documents to Improve Retrieval},
booktitle = {1st {USENIX} Symposium on Internet Technologies and Systems, USITS'97,
Monterey, California, USA, December 8-11, 1997},
publisher = {{USENIX}},
year = {1997},
url = {http://www.usenix.org/publications/library/proceedings/usits97/cutler.html},
timestamp = {Tue, 02 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/usits/CutlerSM97.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/usits/DouglisHR97,
author = {Fred Douglis and
Antonio Haro and
Michael Rabinovich},
title = {{HPP:} {HTML} Macro-Preprocessing to Support Dynamic Document Caching},
booktitle = {1st {USENIX} Symposium on Internet Technologies and Systems, USITS'97,
Monterey, California, USA, December 8-11, 1997},
publisher = {{USENIX}},
year = {1997},
url = {http://www.usenix.org/publications/library/proceedings/usits97/douglis\_hpp.html},
timestamp = {Tue, 02 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/usits/DouglisHR97.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/rfc/rfc2110,
author = {Jacob Palme and
Alex Hopmann},
title = {{MIME} E-mail Encapsulation of Aggregate Documents, such as {HTML}
{(MHTML)}},
journal = {{RFC}},
volume = {2110},
pages = {1--19},
year = {1997},
url = {https://doi.org/10.17487/RFC2110},
doi = {10.17487/RFC2110},
timestamp = {Tue, 14 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/rfc/rfc2110.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/cn/BonhommeR96,
author = {St{\'{e}}phane Bonhomme and
C{\'{e}}cile Roisin},
title = {Interactively Restructuring {HTML} Documents},
journal = {Comput. Networks},
volume = {28},
number = {7-11},
pages = {1075--1084},
year = {1996},
url = {https://doi.org/10.1016/0169-7552(96)00042-6},
doi = {10.1016/0169-7552(96)00042-6},
timestamp = {Wed, 19 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/cn/BonhommeR96.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/cn/Lim95,
author = {Jong{-}Gyun Lim},
title = {Using Coollists to Index {HTML} Documents in the Web},
journal = {Comput. Networks {ISDN} Syst.},
volume = {28},
number = {1{\&}2},
pages = {147--154},
year = {1995},
url = {https://doi.org/10.1016/0169-7552(95)00114-0},
doi = {10.1016/0169-7552(95)00114-0},
timestamp = {Thu, 14 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/cn/Lim95.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/cn/Raggett94,
author = {David Raggett},
title = {A Review of the {HTML} + Document Format},
journal = {Comput. Networks {ISDN} Syst.},
volume = {27},
number = {2},
pages = {135--145},
year = {1994},
url = {https://doi.org/10.1016/0169-7552(94)90127-9},
doi = {10.1016/0169-7552(94)90127-9},
timestamp = {Thu, 14 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/cn/Raggett94.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
a service of 
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
retrieved on 2024-04-25 17:59 CEST from data curated by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
