Stop the war!
Остановите войну!
for scientists:
default search action
Search dblp for Publications
export results for "stream:streams/conf/eval4nlp:"
@inproceedings{DBLP:conf/eval4nlp/AkkasiFK23, author = {Abbas Akkasi and Kathleen C. Fraser and Majid Komeili}, editor = {Daniel Deutsch and Rotem Dror and Steffen Eger and Yang Gao and Christoph Leiter and Juri Opitz and Andreas R{\"{u}}ckl{\'{e}}}, title = {Reference-Free Summarization Evaluation with Large Language Models}, booktitle = {Proceedings of the 4th Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2023, Bali, Indonesia, November 1, 2023}, pages = {193--201}, publisher = {Association for Computational Linguistics}, year = {2023}, url = {https://aclanthology.org/2023.eval4nlp-1.16}, timestamp = {Fri, 12 Apr 2024 20:58:02 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/AkkasiFK23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/BaswaniMS23, author = {Pavan Baswani and Ananya Mukherjee and Manish Shrivastava}, editor = {Daniel Deutsch and Rotem Dror and Steffen Eger and Yang Gao and Christoph Leiter and Juri Opitz and Andreas R{\"{u}}ckl{\'{e}}}, title = {LTRC{\_}IIITH's 2023 Submission for Prompting Large Language Models as Explainable Metrics Task}, booktitle = {Proceedings of the 4th Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2023, Bali, Indonesia, November 1, 2023}, pages = {156--163}, publisher = {Association for Computational Linguistics}, year = {2023}, url = {https://aclanthology.org/2023.eval4nlp-1.13}, timestamp = {Fri, 12 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/BaswaniMS23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/BhatV23, author = {Savita Bhat and Vasudeva Varma}, editor = {Daniel Deutsch and Rotem Dror and Steffen Eger and Yang Gao and Christoph Leiter and Juri Opitz and Andreas R{\"{u}}ckl{\'{e}}}, title = {Large Language Models As Annotators: {A} Preliminary Evaluation For Annotating Low-Resource Language Content}, booktitle = {Proceedings of the 4th Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2023, Bali, Indonesia, November 1, 2023}, pages = {100--107}, publisher = {Association for Computational Linguistics}, year = {2023}, url = {https://aclanthology.org/2023.eval4nlp-1.8}, timestamp = {Fri, 12 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/BhatV23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/BlockCBAD23, author = {Jeremy Block and Yu{-}Peng Chen and Abhilash Budharapu and Lisa Anthony and Bonnie J. Dorr}, editor = {Daniel Deutsch and Rotem Dror and Steffen Eger and Yang Gao and Christoph Leiter and Juri Opitz and Andreas R{\"{u}}ckl{\'{e}}}, title = {Summary Cycles: Exploring the Impact of Prompt Engineering on Large Language Models' Interaction with Interaction Log Information}, booktitle = {Proceedings of the 4th Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2023, Bali, Indonesia, November 1, 2023}, pages = {85--99}, publisher = {Association for Computational Linguistics}, year = {2023}, url = {https://aclanthology.org/2023.eval4nlp-1.7}, timestamp = {Tue, 07 May 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/BlockCBAD23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/ChenE23, author = {Yanran Chen and Steffen Eger}, editor = {Daniel Deutsch and Rotem Dror and Steffen Eger and Yang Gao and Christoph Leiter and Juri Opitz and Andreas R{\"{u}}ckl{\'{e}}}, title = {Transformers Go for the LOLs: Generating (Humourous) Titles from Scientific Abstracts End-to-End}, booktitle = {Proceedings of the 4th Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2023, Bali, Indonesia, November 1, 2023}, pages = {62--84}, publisher = {Association for Computational Linguistics}, year = {2023}, url = {https://aclanthology.org/2023.eval4nlp-1.6}, timestamp = {Fri, 12 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/ChenE23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/DoughmanSQNK23, author = {Jad Doughman and Shady Shehata and Leen Al Qadi and Youssef Nafea and Fakhri Karray}, editor = {Daniel Deutsch and Rotem Dror and Steffen Eger and Yang Gao and Christoph Leiter and Juri Opitz and Andreas R{\"{u}}ckl{\'{e}}}, title = {Can a Prediction's Rank Offer a More Accurate Quantification of Bias? {A} Case Study Measuring Sexism in Debiased Language Models}, booktitle = {Proceedings of the 4th Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2023, Bali, Indonesia, November 1, 2023}, pages = {108--116}, publisher = {Association for Computational Linguistics}, year = {2023}, url = {https://aclanthology.org/2023.eval4nlp-1.9}, timestamp = {Fri, 12 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/DoughmanSQNK23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/KimLHPLJK23, author = {Joonghoon Kim and Sangmin Lee and Seung Hun Han and Saeran Park and Jiyoon Lee and Kiyoon Jeong and Pilsung Kang}, editor = {Daniel Deutsch and Rotem Dror and Steffen Eger and Yang Gao and Christoph Leiter and Juri Opitz and Andreas R{\"{u}}ckl{\'{e}}}, title = {Which is better? Exploring Prompting Strategy For LLM-based Metrics}, booktitle = {Proceedings of the 4th Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2023, Bali, Indonesia, November 1, 2023}, pages = {164--183}, publisher = {Association for Computational Linguistics}, year = {2023}, url = {https://aclanthology.org/2023.eval4nlp-1.14}, timestamp = {Fri, 12 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/KimLHPLJK23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/KolagarSZ23, author = {Zahra Kolagar and Sebastian Steindl and Alessandra Zarcone}, editor = {Daniel Deutsch and Rotem Dror and Steffen Eger and Yang Gao and Christoph Leiter and Juri Opitz and Andreas R{\"{u}}ckl{\'{e}}}, title = {EduQuick: {A} Dataset Toward Evaluating Summarization of Informal Educational Content for Social Media}, booktitle = {Proceedings of the 4th Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2023, Bali, Indonesia, November 1, 2023}, pages = {32--48}, publisher = {Association for Computational Linguistics}, year = {2023}, url = {https://aclanthology.org/2023.eval4nlp-1.4}, timestamp = {Fri, 12 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/KolagarSZ23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/KotonyaKTJ23, author = {Neema Kotonya and Saran Krishnasamy and Joel R. Tetreault and Alejandro Jaimes}, editor = {Daniel Deutsch and Rotem Dror and Steffen Eger and Yang Gao and Christoph Leiter and Juri Opitz and Andreas R{\"{u}}ckl{\'{e}}}, title = {Little Giants: Exploring the Potential of Small LLMs as Evaluation Metrics in Summarization in the Eval4NLP 2023 Shared Task}, booktitle = {Proceedings of the 4th Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2023, Bali, Indonesia, November 1, 2023}, pages = {202--218}, publisher = {Association for Computational Linguistics}, year = {2023}, url = {https://aclanthology.org/2023.eval4nlp-1.17}, timestamp = {Fri, 12 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/KotonyaKTJ23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/LarionovVKPE23, author = {Daniil Larionov and Vasiliy Viskov and George Kokush and Alexander Panchenko and Steffen Eger}, editor = {Daniel Deutsch and Rotem Dror and Steffen Eger and Yang Gao and Christoph Leiter and Juri Opitz and Andreas R{\"{u}}ckl{\'{e}}}, title = {Team {NLLG} submission for Eval4NLP 2023 Shared Task: Retrieval-Augmented In-Context Learning for {NLG} Evaluation}, booktitle = {Proceedings of the 4th Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2023, Bali, Indonesia, November 1, 2023}, pages = {228--234}, publisher = {Association for Computational Linguistics}, year = {2023}, url = {https://aclanthology.org/2023.eval4nlp-1.19}, timestamp = {Fri, 12 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/LarionovVKPE23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/LeiterODGDE23, author = {Christoph Leiter and Juri Opitz and Daniel Deutsch and Yang Gao and Rotem Dror and Steffen Eger}, editor = {Daniel Deutsch and Rotem Dror and Steffen Eger and Yang Gao and Christoph Leiter and Juri Opitz and Andreas R{\"{u}}ckl{\'{e}}}, title = {The Eval4NLP 2023 Shared Task on Prompting Large Language Models as Explainable Metrics}, booktitle = {Proceedings of the 4th Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2023, Bali, Indonesia, November 1, 2023}, pages = {117--138}, publisher = {Association for Computational Linguistics}, year = {2023}, url = {https://aclanthology.org/2023.eval4nlp-1.10}, timestamp = {Fri, 12 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/LeiterODGDE23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/LuL23, author = {Yuan Lu and Yu{-}Ting Lin}, editor = {Daniel Deutsch and Rotem Dror and Steffen Eger and Yang Gao and Christoph Leiter and Juri Opitz and Andreas R{\"{u}}ckl{\'{e}}}, title = {Characterised LLMs Affect its Evaluation of Summary and Translation}, booktitle = {Proceedings of the 4th Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2023, Bali, Indonesia, November 1, 2023}, pages = {184--192}, publisher = {Association for Computational Linguistics}, year = {2023}, url = {https://aclanthology.org/2023.eval4nlp-1.15}, timestamp = {Fri, 12 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/LuL23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/Mahmoudi23, author = {Ghazaleh Mahmoudi}, editor = {Daniel Deutsch and Rotem Dror and Steffen Eger and Yang Gao and Christoph Leiter and Juri Opitz and Andreas R{\"{u}}ckl{\'{e}}}, title = {Exploring Prompting Large Language Models as Explainable Metrics}, booktitle = {Proceedings of the 4th Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2023, Bali, Indonesia, November 1, 2023}, pages = {219--227}, publisher = {Association for Computational Linguistics}, year = {2023}, url = {https://aclanthology.org/2023.eval4nlp-1.18}, timestamp = {Fri, 12 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/Mahmoudi23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/PradhanT23, author = {Abhishek Pradhan and Ketan Kumar Todi}, editor = {Daniel Deutsch and Rotem Dror and Steffen Eger and Yang Gao and Christoph Leiter and Juri Opitz and Andreas R{\"{u}}ckl{\'{e}}}, title = {Understanding Large Language Model Based Metrics for Text Summarization}, booktitle = {Proceedings of the 4th Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2023, Bali, Indonesia, November 1, 2023}, pages = {149--155}, publisher = {Association for Computational Linguistics}, year = {2023}, url = {https://aclanthology.org/2023.eval4nlp-1.12}, timestamp = {Fri, 12 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/PradhanT23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/RainaLG23, author = {Vatsal Raina and Adian Liusie and Mark J. F. Gales}, editor = {Daniel Deutsch and Rotem Dror and Steffen Eger and Yang Gao and Christoph Leiter and Juri Opitz and Andreas R{\"{u}}ckl{\'{e}}}, title = {Assessing Distractors in Multiple-Choice Tests}, booktitle = {Proceedings of the 4th Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2023, Bali, Indonesia, November 1, 2023}, pages = {12--22}, publisher = {Association for Computational Linguistics}, year = {2023}, url = {https://aclanthology.org/2023.eval4nlp-1.2}, timestamp = {Fri, 12 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/RainaLG23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/RamrakhiyaniVPP23, author = {Nitin Ramrakhiyani and Vasudeva Varma and Girish K. Palshikar and Sachin Pawar}, editor = {Daniel Deutsch and Rotem Dror and Steffen Eger and Yang Gao and Christoph Leiter and Juri Opitz and Andreas R{\"{u}}ckl{\'{e}}}, title = {Zero-shot Probing of Pretrained Language Models for Geography Knowledge}, booktitle = {Proceedings of the 4th Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2023, Bali, Indonesia, November 1, 2023}, pages = {49--61}, publisher = {Association for Computational Linguistics}, year = {2023}, url = {https://aclanthology.org/2023.eval4nlp-1.5}, timestamp = {Fri, 12 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/RamrakhiyaniVPP23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/WangCA23, author = {Yixuan Wang and Qingyan Chen and Duygu Ataman}, editor = {Daniel Deutsch and Rotem Dror and Steffen Eger and Yang Gao and Christoph Leiter and Juri Opitz and Andreas R{\"{u}}ckl{\'{e}}}, title = {Delving into Evaluation Metrics for Generation: {A} Thorough Assessment of How Metrics Generalize to Rephrasing Across Languages}, booktitle = {Proceedings of the 4th Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2023, Bali, Indonesia, November 1, 2023}, pages = {23--31}, publisher = {Association for Computational Linguistics}, year = {2023}, url = {https://aclanthology.org/2023.eval4nlp-1.3}, timestamp = {Fri, 12 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/WangCA23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/WeberRBZ23, author = {Lukas Weber and Krishnan Jothi Ramalingam and Matthias Beyer and Axel Zimmermann}, editor = {Daniel Deutsch and Rotem Dror and Steffen Eger and Yang Gao and Christoph Leiter and Juri Opitz and Andreas R{\"{u}}ckl{\'{e}}}, title = {{WRF:} Weighted Rouge-F1 Metric for Entity Recognition}, booktitle = {Proceedings of the 4th Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2023, Bali, Indonesia, November 1, 2023}, pages = {1--11}, publisher = {Association for Computational Linguistics}, year = {2023}, url = {https://aclanthology.org/2023.eval4nlp-1.1}, timestamp = {Mon, 15 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/WeberRBZ23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/ZhangSHYYZ23, author = {Rui Zhang and Fuhai Song and Hui Huang and Jinghao Yuan and Muyun Yang and Tiejun Zhao}, editor = {Daniel Deutsch and Rotem Dror and Steffen Eger and Yang Gao and Christoph Leiter and Juri Opitz and Andreas R{\"{u}}ckl{\'{e}}}, title = {HIT-MI{\&}T Lab's Submission to Eval4NLP 2023 Shared Task}, booktitle = {Proceedings of the 4th Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2023, Bali, Indonesia, November 1, 2023}, pages = {139--148}, publisher = {Association for Computational Linguistics}, year = {2023}, url = {https://aclanthology.org/2023.eval4nlp-1.11}, timestamp = {Fri, 12 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/ZhangSHYYZ23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@proceedings{DBLP:conf/eval4nlp/2023, editor = {Daniel Deutsch and Rotem Dror and Steffen Eger and Yang Gao and Christoph Leiter and Juri Opitz and Andreas R{\"{u}}ckl{\'{e}}}, title = {Proceedings of the 4th Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2023, Bali, Indonesia, November 1, 2023}, publisher = {Association for Computational Linguistics}, year = {2023}, url = {https://aclanthology.org/volumes/2023.eval4nlp-1/}, isbn = {979-8-89176-021-9}, timestamp = {Fri, 12 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/2023.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/AbeYKI22, author = {Kaori Abe and Sho Yokoi and Tomoyuki Kajiwara and Kentaro Inui}, editor = {Daniel Deutsch and Can Udomcharoenchaikit and Juri Opitz and Yang Gao and Marina Fomicheva and Steffen Eger}, title = {Why is sentence similarity benchmark not predictive of application-oriented task performance?}, booktitle = {Proceedings of the 3rd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2022, Online, November 20, 2022}, pages = {70--87}, publisher = {Association for Computational Linguistics}, year = {2022}, url = {https://doi.org/10.18653/v1/2022.eval4nlp-1.8}, doi = {10.18653/V1/2022.EVAL4NLP-1.8}, timestamp = {Tue, 16 Apr 2024 16:43:29 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/AbeYKI22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/ChenSD22, author = {Guanyi Chen and Fahime Same and Kees van Deemter}, editor = {Daniel Deutsch and Can Udomcharoenchaikit and Juri Opitz and Yang Gao and Marina Fomicheva and Steffen Eger}, title = {Assessing Neural Referential Form Selectors on a Realistic Multilingual Dataset}, booktitle = {Proceedings of the 3rd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2022, Online, November 20, 2022}, pages = {103--114}, publisher = {Association for Computational Linguistics}, year = {2022}, url = {https://doi.org/10.18653/v1/2022.eval4nlp-1.11}, doi = {10.18653/V1/2022.EVAL4NLP-1.11}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/ChenSD22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/ChiKLLC22, author = {Ryan Chi and Nathan Kim and Patrick Liu and Zander Lack and Ethan A. Chi}, editor = {Daniel Deutsch and Can Udomcharoenchaikit and Juri Opitz and Yang Gao and Marina Fomicheva and Steffen Eger}, title = {{GLARE:} Generative Left-to-right AdversaRial Examples}, booktitle = {Proceedings of the 3rd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2022, Online, November 20, 2022}, pages = {44--50}, publisher = {Association for Computational Linguistics}, year = {2022}, url = {https://doi.org/10.18653/v1/2022.eval4nlp-1.5}, doi = {10.18653/V1/2022.EVAL4NLP-1.5}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/ChiKLLC22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/GeraN22, author = {Parush Gera and Tempestt J. Neal}, editor = {Daniel Deutsch and Can Udomcharoenchaikit and Juri Opitz and Yang Gao and Marina Fomicheva and Steffen Eger}, title = {A Comparative Analysis of Stance Detection Approaches and Datasets}, booktitle = {Proceedings of the 3rd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2022, Online, November 20, 2022}, pages = {58--69}, publisher = {Association for Computational Linguistics}, year = {2022}, url = {https://doi.org/10.18653/v1/2022.eval4nlp-1.7}, doi = {10.18653/V1/2022.EVAL4NLP-1.7}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/GeraN22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/HigashiyamaIUOS22, author = {Shohei Higashiyama and Masao Ideuchi and Masao Utiyama and Yoshiaki Oida and Eiichiro Sumita}, editor = {Daniel Deutsch and Can Udomcharoenchaikit and Juri Opitz and Yang Gao and Marina Fomicheva and Steffen Eger}, title = {A Japanese Corpus of Many Specialized Domains for Word Segmentation and Part-of-Speech Tagging}, booktitle = {Proceedings of the 3rd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2022, Online, November 20, 2022}, pages = {1--10}, publisher = {Association for Computational Linguistics}, year = {2022}, url = {https://doi.org/10.18653/v1/2022.eval4nlp-1.1}, doi = {10.18653/V1/2022.EVAL4NLP-1.1}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/HigashiyamaIUOS22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/KrubinskiP22, author = {Mateusz Krubi'nski and Pavel Pecina}, editor = {Daniel Deutsch and Can Udomcharoenchaikit and Juri Opitz and Yang Gao and Marina Fomicheva and Steffen Eger}, title = {From {COMET} to {COMES} - Can Summary Evaluation Benefit from Translation Evaluation?}, booktitle = {Proceedings of the 3rd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2022, Online, November 20, 2022}, pages = {21--31}, publisher = {Association for Computational Linguistics}, year = {2022}, url = {https://doi.org/10.18653/v1/2022.eval4nlp-1.3}, doi = {10.18653/V1/2022.EVAL4NLP-1.3}, timestamp = {Sat, 27 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/KrubinskiP22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/LiSMATBI22, author = {Yunmeng Li and Jun Suzuki and Makoto Morishita and Kaori Abe and Ryoko Tokuhisa and Ana Brassard and Kentaro Inui}, editor = {Daniel Deutsch and Can Udomcharoenchaikit and Juri Opitz and Yang Gao and Marina Fomicheva and Steffen Eger}, title = {Chat Translation Error Detection for Assisting Cross-lingual Communications}, booktitle = {Proceedings of the 3rd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2022, Online, November 20, 2022}, pages = {88--95}, publisher = {Association for Computational Linguistics}, year = {2022}, url = {https://doi.org/10.18653/v1/2022.eval4nlp-1.9}, doi = {10.18653/V1/2022.EVAL4NLP-1.9}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/LiSMATBI22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/OpitzF22, author = {Juri Opitz and Anette Frank}, editor = {Daniel Deutsch and Can Udomcharoenchaikit and Juri Opitz and Yang Gao and Marina Fomicheva and Steffen Eger}, title = {Better Smatch = Better Parser? {AMR} evaluation is not so simple anymore}, booktitle = {Proceedings of the 3rd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2022, Online, November 20, 2022}, pages = {32--43}, publisher = {Association for Computational Linguistics}, year = {2022}, url = {https://doi.org/10.18653/v1/2022.eval4nlp-1.4}, doi = {10.18653/V1/2022.EVAL4NLP-1.4}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/OpitzF22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/RoccaV22, author = {Roberta Rocca and Alejandro de la Vega}, editor = {Daniel Deutsch and Can Udomcharoenchaikit and Juri Opitz and Yang Gao and Marina Fomicheva and Steffen Eger}, title = {Evaluating the role of non-lexical markers in GPT-2's language modeling behavior}, booktitle = {Proceedings of the 3rd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2022, Online, November 20, 2022}, pages = {96--102}, publisher = {Association for Computational Linguistics}, year = {2022}, url = {https://doi.org/10.18653/v1/2022.eval4nlp-1.10}, doi = {10.18653/V1/2022.EVAL4NLP-1.10}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/RoccaV22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/Wang22, author = {Zhengxiang Wang}, editor = {Daniel Deutsch and Can Udomcharoenchaikit and Juri Opitz and Yang Gao and Marina Fomicheva and Steffen Eger}, title = {Random Text Perturbations Work, but not Always}, booktitle = {Proceedings of the 3rd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2022, Online, November 20, 2022}, pages = {51--57}, publisher = {Association for Computational Linguistics}, year = {2022}, url = {https://doi.org/10.18653/v1/2022.eval4nlp-1.6}, doi = {10.18653/V1/2022.EVAL4NLP-1.6}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/Wang22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/ZhouZCK22, author = {Shohei Zhou and Alisha Zachariah and Devin Conathan and Jeffery Kline}, editor = {Daniel Deutsch and Can Udomcharoenchaikit and Juri Opitz and Yang Gao and Marina Fomicheva and Steffen Eger}, title = {Assessing Resource-Performance Trade-off of Natural Language Models using Data Envelopment Analysis}, booktitle = {Proceedings of the 3rd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2022, Online, November 20, 2022}, pages = {11--20}, publisher = {Association for Computational Linguistics}, year = {2022}, url = {https://doi.org/10.18653/v1/2022.eval4nlp-1.2}, doi = {10.18653/V1/2022.EVAL4NLP-1.2}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/ZhouZCK22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@proceedings{DBLP:conf/eval4nlp/2022, editor = {Daniel Deutsch and Can Udomcharoenchaikit and Juri Opitz and Yang Gao and Marina Fomicheva and Steffen Eger}, title = {Proceedings of the 3rd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2022, Online, November 20, 2022}, publisher = {Association for Computational Linguistics}, year = {2022}, url = {https://aclanthology.org/volumes/2022.eval4nlp-1/}, isbn = {978-1-959429-00-5}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/2022.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/ChenCFE21, author = {David Chen and Maury Courtland and Adam Faulkner and Aysu Ezen{-}Can}, editor = {Yang Gao and Steffen Eger and Wei Zhao and Piyawat Lertvittayakumjorn and Marina Fomicheva}, title = {Error-Sensitive Evaluation for Ordinal Target Variables}, booktitle = {Proceedings of the 2nd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2021, Punta Cana, Dominican Republic, November 10, 2021}, pages = {189--199}, publisher = {Association for Computational Linguistics}, year = {2021}, url = {https://aclanthology.org/2021.eval4nlp-1.19}, timestamp = {Tue, 16 Apr 2024 16:43:29 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/ChenCFE21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/Ehara21, author = {Yo Ehara}, editor = {Yang Gao and Steffen Eger and Wei Zhao and Piyawat Lertvittayakumjorn and Marina Fomicheva}, title = {Evaluation of Unsupervised Automatic Readability Assessors Using Rank Correlations}, booktitle = {Proceedings of the 2nd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2021, Punta Cana, Dominican Republic, November 10, 2021}, pages = {62--72}, publisher = {Association for Computational Linguistics}, year = {2021}, url = {https://aclanthology.org/2021.eval4nlp-1.7}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/Ehara21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/EksiGSV21, author = {Melda Eksi and Erik Gelbing and Jonathan Stieber and Chi Viet Vu}, editor = {Yang Gao and Steffen Eger and Wei Zhao and Piyawat Lertvittayakumjorn and Marina Fomicheva}, title = {Explaining Errors in Machine Translation with Absolute Gradient Ensembles}, booktitle = {Proceedings of the 2nd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2021, Punta Cana, Dominican Republic, November 10, 2021}, pages = {238--249}, publisher = {Association for Computational Linguistics}, year = {2021}, url = {https://aclanthology.org/2021.eval4nlp-1.23}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/EksiGSV21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/FomichevaLZEG21, author = {Marina Fomicheva and Piyawat Lertvittayakumjorn and Wei Zhao and Steffen Eger and Yang Gao}, editor = {Yang Gao and Steffen Eger and Wei Zhao and Piyawat Lertvittayakumjorn and Marina Fomicheva}, title = {The Eval4NLP Shared Task on Explainable Quality Estimation: Overview and Results}, booktitle = {Proceedings of the 2nd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2021, Punta Cana, Dominican Republic, November 10, 2021}, pages = {165--178}, publisher = {Association for Computational Linguistics}, year = {2021}, url = {https://aclanthology.org/2021.eval4nlp-1.17}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/FomichevaLZEG21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/GargKSS21, author = {Ayush Garg and Sammed S. Kagi and Vivek Srivastava and Mayank Singh}, editor = {Yang Gao and Steffen Eger and Wei Zhao and Piyawat Lertvittayakumjorn and Marina Fomicheva}, title = {{MIPE:} {A} Metric Independent Pipeline for Effective Code-Mixed {NLG} Evaluation}, booktitle = {Proceedings of the 2nd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2021, Punta Cana, Dominican Republic, November 10, 2021}, pages = {123--132}, publisher = {Association for Computational Linguistics}, year = {2021}, url = {https://aclanthology.org/2021.eval4nlp-1.13}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/GargKSS21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/GarneauL21, author = {Nicolas Garneau and Luc Lamontagne}, editor = {Yang Gao and Steffen Eger and Wei Zhao and Piyawat Lertvittayakumjorn and Marina Fomicheva}, title = {Trainable Ranking Models to Evaluate the Semantic Accuracy of Data-to-Text Neural Generator}, booktitle = {Proceedings of the 2nd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2021, Punta Cana, Dominican Republic, November 10, 2021}, pages = {51--61}, publisher = {Association for Computational Linguistics}, year = {2021}, url = {https://aclanthology.org/2021.eval4nlp-1.6}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/GarneauL21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/GianolaBGLPZ21, author = {Lucie Gianola and Hicham El Boukkouri and Cyril Grouin and Thomas Lavergne and Patrick Paroubek and Pierre Zweigenbaum}, editor = {Yang Gao and Steffen Eger and Wei Zhao and Piyawat Lertvittayakumjorn and Marina Fomicheva}, title = {Differential Evaluation: a Qualitative Analysis of Natural Language Processing System Behavior Based Upon Data Resistance to Processing}, booktitle = {Proceedings of the 2nd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2021, Punta Cana, Dominican Republic, November 10, 2021}, pages = {1--10}, publisher = {Association for Computational Linguistics}, year = {2021}, url = {https://aclanthology.org/2021.eval4nlp-1.1}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/GianolaBGLPZ21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/KabirC21, author = {Tasnim Kabir and Marine Carpuat}, editor = {Yang Gao and Steffen Eger and Wei Zhao and Piyawat Lertvittayakumjorn and Marina Fomicheva}, title = {The {UMD} Submission to the Explainable {MT} Quality Estimation Shared Task: Combining Explanation Models with Sequence Labeling}, booktitle = {Proceedings of the 2nd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2021, Punta Cana, Dominican Republic, November 10, 2021}, pages = {230--237}, publisher = {Association for Computational Linguistics}, year = {2021}, url = {https://aclanthology.org/2021.eval4nlp-1.22}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/KabirC21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/KhuranaNF21, author = {Urja Khurana and Eric T. Nalisnick and Antske Fokkens}, editor = {Yang Gao and Steffen Eger and Wei Zhao and Piyawat Lertvittayakumjorn and Marina Fomicheva}, title = {How Emotionally Stable is ALBERT? Testing Robustness with Stochastic Weight Averaging on a Sentiment Analysis Task}, booktitle = {Proceedings of the 2nd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2021, Punta Cana, Dominican Republic, November 10, 2021}, pages = {16--31}, publisher = {Association for Computational Linguistics}, year = {2021}, url = {https://aclanthology.org/2021.eval4nlp-1.3}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/KhuranaNF21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/Leiter21, author = {Christoph Wolfgang Leiter}, editor = {Yang Gao and Steffen Eger and Wei Zhao and Piyawat Lertvittayakumjorn and Marina Fomicheva}, title = {Reference-Free Word- and Sentence-Level Translation Evaluation with Token-Matching Metrics}, booktitle = {Proceedings of the 2nd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2021, Punta Cana, Dominican Republic, November 10, 2021}, pages = {157--164}, publisher = {Association for Computational Linguistics}, year = {2021}, url = {https://aclanthology.org/2021.eval4nlp-1.16}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/Leiter21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/LentYYNZRL21, author = {Heather Lent and Semih Yavuz and Tao Yu and Tong Niu and Yingbo Zhou and Dragomir Radev and Xi Victoria Lin}, editor = {Yang Gao and Steffen Eger and Wei Zhao and Piyawat Lertvittayakumjorn and Marina Fomicheva}, title = {Testing Cross-Database Semantic Parsers With Canonical Utterances}, booktitle = {Proceedings of the 2nd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2021, Punta Cana, Dominican Republic, November 10, 2021}, pages = {73--83}, publisher = {Association for Computational Linguistics}, year = {2021}, url = {https://aclanthology.org/2021.eval4nlp-1.8}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/LentYYNZRL21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/LiuMG21, author = {Yang Liu and Alan Medlar and Dorota Glowacka}, editor = {Yang Gao and Steffen Eger and Wei Zhao and Piyawat Lertvittayakumjorn and Marina Fomicheva}, title = {Statistically Significant Detection of Semantic Shifts using Contextual Word Embeddings}, booktitle = {Proceedings of the 2nd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2021, Punta Cana, Dominican Republic, November 10, 2021}, pages = {104--113}, publisher = {Association for Computational Linguistics}, year = {2021}, url = {https://aclanthology.org/2021.eval4nlp-1.11}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/LiuMG21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/ManningS21, author = {Emma Manning and Nathan Schneider}, editor = {Yang Gao and Steffen Eger and Wei Zhao and Piyawat Lertvittayakumjorn and Marina Fomicheva}, title = {Referenceless Parsing-Based Evaluation of AMR-to-English Generation}, booktitle = {Proceedings of the 2nd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2021, Punta Cana, Dominican Republic, November 10, 2021}, pages = {114--122}, publisher = {Association for Computational Linguistics}, year = {2021}, url = {https://aclanthology.org/2021.eval4nlp-1.12}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/ManningS21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/MurauerS21, author = {Benjamin Murauer and G{\"{u}}nther Specht}, editor = {Yang Gao and Steffen Eger and Wei Zhao and Piyawat Lertvittayakumjorn and Marina Fomicheva}, title = {Developing a Benchmark for Reducing Data Bias in Authorship Attribution}, booktitle = {Proceedings of the 2nd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2021, Punta Cana, Dominican Republic, November 10, 2021}, pages = {179--188}, publisher = {Association for Computational Linguistics}, year = {2021}, url = {https://aclanthology.org/2021.eval4nlp-1.18}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/MurauerS21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/PalenMichelHL21, author = {Chester Palen{-}Michel and Nolan Holley and Constantine Lignos}, editor = {Yang Gao and Steffen Eger and Wei Zhao and Piyawat Lertvittayakumjorn and Marina Fomicheva}, title = {SeqScore: Addressing Barriers to Reproducible Named Entity Recognition Evaluation}, booktitle = {Proceedings of the 2nd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2021, Punta Cana, Dominican Republic, November 10, 2021}, pages = {40--50}, publisher = {Association for Computational Linguistics}, year = {2021}, url = {https://aclanthology.org/2021.eval4nlp-1.5}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/PalenMichelHL21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/PolakSB21, author = {Peter Pol{\'{a}}k and Muskaan Singh and Ondrej Bojar}, editor = {Yang Gao and Steffen Eger and Wei Zhao and Piyawat Lertvittayakumjorn and Marina Fomicheva}, title = {Explainable Quality Estimation: {CUNI} Eval4NLP Submission}, booktitle = {Proceedings of the 2nd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2021, Punta Cana, Dominican Republic, November 10, 2021}, pages = {250--255}, publisher = {Association for Computational Linguistics}, year = {2021}, url = {https://aclanthology.org/2021.eval4nlp-1.24}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/PolakSB21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/RubinoFM21, author = {Raphael Rubino and Atsushi Fujita and Benjamin Marie}, editor = {Yang Gao and Steffen Eger and Wei Zhao and Piyawat Lertvittayakumjorn and Marina Fomicheva}, title = {Error Identification for Machine Translation with Metric Embedding and Attention}, booktitle = {Proceedings of the 2nd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2021, Punta Cana, Dominican Republic, November 10, 2021}, pages = {146--156}, publisher = {Association for Computational Linguistics}, year = {2021}, url = {https://aclanthology.org/2021.eval4nlp-1.15}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/RubinoFM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/SrivastavaS21, author = {Vivek Srivastava and Mayank Singh}, editor = {Yang Gao and Steffen Eger and Wei Zhao and Piyawat Lertvittayakumjorn and Marina Fomicheva}, title = {HinGE: {A} Dataset for Generation and Evaluation of Code-Mixed Hinglish Text}, booktitle = {Proceedings of the 2nd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2021, Punta Cana, Dominican Republic, November 10, 2021}, pages = {200--208}, publisher = {Association for Computational Linguistics}, year = {2021}, url = {https://aclanthology.org/2021.eval4nlp-1.20}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/SrivastavaS21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/TerreauGV21, author = {Enzo Terreau and Antoine Gourru and Julien Velcin}, editor = {Yang Gao and Steffen Eger and Wei Zhao and Piyawat Lertvittayakumjorn and Marina Fomicheva}, title = {Writing Style Author Embedding Evaluation}, booktitle = {Proceedings of the 2nd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2021, Punta Cana, Dominican Republic, November 10, 2021}, pages = {84--93}, publisher = {Association for Computational Linguistics}, year = {2021}, url = {https://aclanthology.org/2021.eval4nlp-1.9}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/TerreauGV21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/TikhonovSY21, author = {Alexey Tikhonov and Igor Samenko and Ivan P. Yamshchikov}, editor = {Yang Gao and Steffen Eger and Wei Zhao and Piyawat Lertvittayakumjorn and Marina Fomicheva}, title = {StoryDB: Broad Multi-language Narrative Dataset}, booktitle = {Proceedings of the 2nd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2021, Punta Cana, Dominican Republic, November 10, 2021}, pages = {32--39}, publisher = {Association for Computational Linguistics}, year = {2021}, url = {https://aclanthology.org/2021.eval4nlp-1.4}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/TikhonovSY21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/TrevisoGRM21, author = {Marcos V. Treviso and Nuno Miguel Guerreiro and Ricardo Rei and Andr{\'{e}} F. T. Martins}, editor = {Yang Gao and Steffen Eger and Wei Zhao and Piyawat Lertvittayakumjorn and Marina Fomicheva}, title = {IST-Unbabel 2021 Submission for the Explainable Quality Estimation Shared Task}, booktitle = {Proceedings of the 2nd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2021, Punta Cana, Dominican Republic, November 10, 2021}, pages = {133--145}, publisher = {Association for Computational Linguistics}, year = {2021}, url = {https://aclanthology.org/2021.eval4nlp-1.14}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/TrevisoGRM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/VasilyevB21, author = {Oleg V. Vasilyev and John Bohannon}, editor = {Yang Gao and Steffen Eger and Wei Zhao and Piyawat Lertvittayakumjorn and Marina Fomicheva}, title = {{ESTIME:} Estimation of Summary-to-Text Inconsistency by Mismatched Embeddings}, booktitle = {Proceedings of the 2nd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2021, Punta Cana, Dominican Republic, November 10, 2021}, pages = {94--103}, publisher = {Association for Computational Linguistics}, year = {2021}, url = {https://aclanthology.org/2021.eval4nlp-1.10}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/VasilyevB21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/WysockiFLF21, author = {Oskar Wysocki and Malina Florea and D{\'{o}}nal Landers and Andr{\'{e}} Freitas}, editor = {Yang Gao and Steffen Eger and Wei Zhao and Piyawat Lertvittayakumjorn and Marina Fomicheva}, title = {What is SemEval evaluating? {A} Systematic Analysis of Evaluation Campaigns in {NLP}}, booktitle = {Proceedings of the 2nd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2021, Punta Cana, Dominican Republic, November 10, 2021}, pages = {209--229}, publisher = {Association for Computational Linguistics}, year = {2021}, url = {https://aclanthology.org/2021.eval4nlp-1.21}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/WysockiFLF21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/ZengYYJJ21, author = {Qingkai Zeng and Mengxia Yu and Wenhao Yu and Tianwen Jiang and Meng Jiang}, editor = {Yang Gao and Steffen Eger and Wei Zhao and Piyawat Lertvittayakumjorn and Marina Fomicheva}, title = {Validating Label Consistency in {NER} Data Annotation}, booktitle = {Proceedings of the 2nd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2021, Punta Cana, Dominican Republic, November 10, 2021}, pages = {11--15}, publisher = {Association for Computational Linguistics}, year = {2021}, url = {https://aclanthology.org/2021.eval4nlp-1.2}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/ZengYYJJ21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@proceedings{DBLP:conf/eval4nlp/2021, editor = {Yang Gao and Steffen Eger and Wei Zhao and Piyawat Lertvittayakumjorn and Marina Fomicheva}, title = {Proceedings of the 2nd Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2021, Punta Cana, Dominican Republic, November 10, 2021}, publisher = {Association for Computational Linguistics}, year = {2021}, url = {https://aclanthology.org/volumes/2021.eval4nlp-1/}, isbn = {978-1-954085-88-6}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/2021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/AndersenBSCA20, author = {Jesper Brink Andersen and Mikkel Bak Bertelsen and Mikkel H{\o}rby Schou and Manuel R. Ciosici and Ira Assent}, editor = {Steffen Eger and Yang Gao and Maxime Peyrard and Wei Zhao and Eduard H. Hovy}, title = {One of these words is not like the other: a reproduction of outlier identification using non-contextual word representations}, booktitle = {Proceedings of the First Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2020, Online, November 20, 2020}, pages = {120--130}, publisher = {Association for Computational Linguistics}, year = {2020}, url = {https://doi.org/10.18653/v1/2020.eval4nlp-1.12}, doi = {10.18653/V1/2020.EVAL4NLP-1.12}, timestamp = {Tue, 16 Apr 2024 16:43:29 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/AndersenBSCA20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/BremermanKOP20, author = {Jacob Bremerman and Huda Khayrallah and Douglas W. Oard and Matt Post}, editor = {Steffen Eger and Yang Gao and Maxime Peyrard and Wei Zhao and Eduard H. Hovy}, title = {On the Evaluation of Machine Translation n-best Lists}, booktitle = {Proceedings of the First Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2020, Online, November 20, 2020}, pages = {60--68}, publisher = {Association for Computational Linguistics}, year = {2020}, url = {https://doi.org/10.18653/v1/2020.eval4nlp-1.7}, doi = {10.18653/V1/2020.EVAL4NLP-1.7}, timestamp = {Sat, 27 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/BremermanKOP20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/ChenDLS20, author = {Xi Chen and Nan Ding and Tomer Levinboim and Radu Soricut}, editor = {Steffen Eger and Yang Gao and Maxime Peyrard and Wei Zhao and Eduard H. Hovy}, title = {Improving Text Generation Evaluation with Batch Centering and Tempered Word Mover Distance}, booktitle = {Proceedings of the First Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2020, Online, November 20, 2020}, pages = {51--59}, publisher = {Association for Computational Linguistics}, year = {2020}, url = {https://doi.org/10.18653/v1/2020.eval4nlp-1.6}, doi = {10.18653/V1/2020.EVAL4NLP-1.6}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/ChenDLS20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/DudyB20, author = {Shiran Dudy and Steven Bedrick}, editor = {Steffen Eger and Yang Gao and Maxime Peyrard and Wei Zhao and Eduard H. Hovy}, title = {Are Some Words Worth More than Others?}, booktitle = {Proceedings of the First Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2020, Online, November 20, 2020}, pages = {131--142}, publisher = {Association for Computational Linguistics}, year = {2020}, url = {https://doi.org/10.18653/v1/2020.eval4nlp-1.13}, doi = {10.18653/V1/2020.EVAL4NLP-1.13}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/DudyB20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/EthayarajhS20, author = {Kawin Ethayarajh and Dorsa Sadigh}, editor = {Steffen Eger and Yang Gao and Maxime Peyrard and Wei Zhao and Eduard H. Hovy}, title = {{BLEU} Neighbors: {A} Reference-less Approach to Automatic Evaluation}, booktitle = {Proceedings of the First Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2020, Online, November 20, 2020}, pages = {40--50}, publisher = {Association for Computational Linguistics}, year = {2020}, url = {https://doi.org/10.18653/v1/2020.eval4nlp-1.5}, doi = {10.18653/V1/2020.EVAL4NLP-1.5}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/EthayarajhS20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/GashteovskiGKHM20, author = {Kiril Gashteovski and Rainer Gemulla and Bhushan Kotnis and Sven Hertling and Christian Meilicke}, editor = {Steffen Eger and Yang Gao and Maxime Peyrard and Wei Zhao and Eduard H. Hovy}, title = {On Aligning OpenIE Extractions with Knowledge Bases: {A} Case Study}, booktitle = {Proceedings of the First Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2020, Online, November 20, 2020}, pages = {143--154}, publisher = {Association for Computational Linguistics}, year = {2020}, url = {https://doi.org/10.18653/v1/2020.eval4nlp-1.14}, doi = {10.18653/V1/2020.EVAL4NLP-1.14}, timestamp = {Sat, 27 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/GashteovskiGKHM20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/IskenderPM20, author = {Neslihan Iskender and Tim Polzehl and Sebastian M{\"{o}}ller}, editor = {Steffen Eger and Yang Gao and Maxime Peyrard and Wei Zhao and Eduard H. Hovy}, title = {Best Practices for Crowd-based Evaluation of German Summarization: Comparing Crowd, Expert and Automatic Evaluation}, booktitle = {Proceedings of the First Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2020, Online, November 20, 2020}, pages = {164--175}, publisher = {Association for Computational Linguistics}, year = {2020}, url = {https://doi.org/10.18653/v1/2020.eval4nlp-1.16}, doi = {10.18653/V1/2020.EVAL4NLP-1.16}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/IskenderPM20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/JhaBLPCZM20, author = {Rahul Jha and Keping Bi and Yang Li and Mahdi Pakdaman and Asli Celikyilmaz and Ivan Zhiboedov and Kieran McDonald}, editor = {Steffen Eger and Yang Gao and Maxime Peyrard and Wei Zhao and Eduard H. Hovy}, title = {Artemis: {A} Novel Annotation Methodology for Indicative Single Document Summarization}, booktitle = {Proceedings of the First Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2020, Online, November 20, 2020}, pages = {69--78}, publisher = {Association for Computational Linguistics}, year = {2020}, url = {https://doi.org/10.18653/v1/2020.eval4nlp-1.8}, doi = {10.18653/V1/2020.EVAL4NLP-1.8}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/JhaBLPCZM20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/LeeYDKBJ20, author = {Hwanhee Lee and Seunghyun Yoon and Franck Dernoncourt and Doo Soon Kim and Trung Bui and Kyomin Jung}, editor = {Steffen Eger and Yang Gao and Maxime Peyrard and Wei Zhao and Eduard H. Hovy}, title = {ViLBERTScore: Evaluating Image Caption Using Vision-and-Language {BERT}}, booktitle = {Proceedings of the First Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2020, Online, November 20, 2020}, pages = {34--39}, publisher = {Association for Computational Linguistics}, year = {2020}, url = {https://doi.org/10.18653/v1/2020.eval4nlp-1.4}, doi = {10.18653/V1/2020.EVAL4NLP-1.4}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/LeeYDKBJ20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/LuxSL20, author = {Klaus{-}Michael Lux and Maya Sappelli and Martha A. Larson}, editor = {Steffen Eger and Yang Gao and Maxime Peyrard and Wei Zhao and Eduard H. Hovy}, title = {Truth or Error? Towards systematic analysis of factual errors in abstractive summaries}, booktitle = {Proceedings of the First Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2020, Online, November 20, 2020}, pages = {1--10}, publisher = {Association for Computational Linguistics}, year = {2020}, url = {https://doi.org/10.18653/v1/2020.eval4nlp-1.1}, doi = {10.18653/V1/2020.EVAL4NLP-1.1}, timestamp = {Sat, 27 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/LuxSL20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/NiuP20, author = {Jingcheng Niu and Gerald Penn}, editor = {Steffen Eger and Yang Gao and Maxime Peyrard and Wei Zhao and Eduard H. Hovy}, title = {Grammaticality and Language Modelling}, booktitle = {Proceedings of the First Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2020, Online, November 20, 2020}, pages = {110--119}, publisher = {Association for Computational Linguistics}, year = {2020}, url = {https://doi.org/10.18653/v1/2020.eval4nlp-1.11}, doi = {10.18653/V1/2020.EVAL4NLP-1.11}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/NiuP20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/Poliak20, author = {Adam Poliak}, editor = {Steffen Eger and Yang Gao and Maxime Peyrard and Wei Zhao and Eduard H. Hovy}, title = {A survey on Recognizing Textual Entailment as an {NLP} Evaluation}, booktitle = {Proceedings of the First Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2020, Online, November 20, 2020}, pages = {92--109}, publisher = {Association for Computational Linguistics}, year = {2020}, url = {https://doi.org/10.18653/v1/2020.eval4nlp-1.10}, doi = {10.18653/V1/2020.EVAL4NLP-1.10}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/Poliak20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/SedocU20, author = {Jo{\~{a}}o Sedoc and Lyle H. Ungar}, editor = {Steffen Eger and Yang Gao and Maxime Peyrard and Wei Zhao and Eduard H. Hovy}, title = {Item Response Theory for Efficient Human Evaluation of Chatbots}, booktitle = {Proceedings of the First Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2020, Online, November 20, 2020}, pages = {21--33}, publisher = {Association for Computational Linguistics}, year = {2020}, url = {https://doi.org/10.18653/v1/2020.eval4nlp-1.3}, doi = {10.18653/V1/2020.EVAL4NLP-1.3}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/SedocU20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/StringhamI20, author = {Nathan Stringham and Mike Izbicki}, editor = {Steffen Eger and Yang Gao and Maxime Peyrard and Wei Zhao and Eduard H. Hovy}, title = {Evaluating Word Embeddings on Low-Resource Languages}, booktitle = {Proceedings of the First Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2020, Online, November 20, 2020}, pages = {176--186}, publisher = {Association for Computational Linguistics}, year = {2020}, url = {https://doi.org/10.18653/v1/2020.eval4nlp-1.17}, doi = {10.18653/V1/2020.EVAL4NLP-1.17}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/StringhamI20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/VasilyevDB20, author = {Oleg V. Vasilyev and Vedant Dharnidharka and John Bohannon}, editor = {Steffen Eger and Yang Gao and Maxime Peyrard and Wei Zhao and Eduard H. Hovy}, title = {Fill in the {BLANC:} Human-free quality estimation of document summaries}, booktitle = {Proceedings of the First Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2020, Online, November 20, 2020}, pages = {11--20}, publisher = {Association for Computational Linguistics}, year = {2020}, url = {https://doi.org/10.18653/v1/2020.eval4nlp-1.2}, doi = {10.18653/V1/2020.EVAL4NLP-1.2}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/VasilyevDB20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/WeckerFA20, author = {Hanna Wecker and Annemarie Friedrich and Heike Adel}, editor = {Steffen Eger and Yang Gao and Maxime Peyrard and Wei Zhao and Eduard H. Hovy}, title = {ClusterDataSplit: Exploring Challenging Clustering-Based Data Splits for Model Performance Evaluation}, booktitle = {Proceedings of the First Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2020, Online, November 20, 2020}, pages = {155--163}, publisher = {Association for Computational Linguistics}, year = {2020}, url = {https://doi.org/10.18653/v1/2020.eval4nlp-1.15}, doi = {10.18653/V1/2020.EVAL4NLP-1.15}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/WeckerFA20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eval4nlp/YacoubyA20, author = {Reda Yacouby and Dustin Axman}, editor = {Steffen Eger and Yang Gao and Maxime Peyrard and Wei Zhao and Eduard H. Hovy}, title = {Probabilistic Extension of Precision, Recall, and {F1} Score for More Thorough Evaluation of Classification Models}, booktitle = {Proceedings of the First Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2020, Online, November 20, 2020}, pages = {79--91}, publisher = {Association for Computational Linguistics}, year = {2020}, url = {https://doi.org/10.18653/v1/2020.eval4nlp-1.9}, doi = {10.18653/V1/2020.EVAL4NLP-1.9}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/YacoubyA20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@proceedings{DBLP:conf/eval4nlp/2020, editor = {Steffen Eger and Yang Gao and Maxime Peyrard and Wei Zhao and Eduard H. Hovy}, title = {Proceedings of the First Workshop on Evaluation and Comparison of {NLP} Systems, Eval4NLP 2020, Online, November 20, 2020}, publisher = {Association for Computational Linguistics}, year = {2020}, url = {https://www.aclweb.org/anthology/volumes/2020.eval4nlp-1/}, isbn = {978-1-952148-82-8}, timestamp = {Tue, 16 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eval4nlp/2020.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
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.