@proceedings{eval4nlp-2020-evaluation,
    title = "Proceedings of the First Workshop on Evaluation and Comparison of NLP Systems",
    editor = "Eger, Steffen  and
      Gao, Yang  and
      Peyrard, Maxime  and
      Zhao, Wei  and
      Hovy, Eduard",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/volume-fixes/2020.eval4nlp-1.0/",
    doi = "10.18653/v1/2020.eval4nlp-1.0"
}
@inproceedings{lux-etal-2020-truth,
    title = "Truth or Error? Towards systematic analysis of factual errors in abstractive summaries",
    author = "Lux, Klaus-Michael  and
      Sappelli, Maya  and
      Larson, Martha",
    editor = "Eger, Steffen  and
      Gao, Yang  and
      Peyrard, Maxime  and
      Zhao, Wei  and
      Hovy, Eduard",
    booktitle = "Proceedings of the First Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/volume-fixes/2020.eval4nlp-1.1/",
    doi = "10.18653/v1/2020.eval4nlp-1.1",
    pages = "1--10"
}
@inproceedings{vasilyev-etal-2020-fill,
    title = "Fill in the {BLANC}: Human-free quality estimation of document summaries",
    author = "Vasilyev, Oleg  and
      Dharnidharka, Vedant  and
      Bohannon, John",
    editor = "Eger, Steffen  and
      Gao, Yang  and
      Peyrard, Maxime  and
      Zhao, Wei  and
      Hovy, Eduard",
    booktitle = "Proceedings of the First Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/volume-fixes/2020.eval4nlp-1.2/",
    doi = "10.18653/v1/2020.eval4nlp-1.2",
    pages = "11--20"
}
@inproceedings{sedoc-ungar-2020-item,
    title = "Item Response Theory for Efficient Human Evaluation of Chatbots",
    author = "Sedoc, Jo{\~a}o  and
      Ungar, Lyle",
    editor = "Eger, Steffen  and
      Gao, Yang  and
      Peyrard, Maxime  and
      Zhao, Wei  and
      Hovy, Eduard",
    booktitle = "Proceedings of the First Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/volume-fixes/2020.eval4nlp-1.3/",
    doi = "10.18653/v1/2020.eval4nlp-1.3",
    pages = "21--33"
}
@inproceedings{lee-etal-2020-vilbertscore,
    title = "{V}i{LBERTS}core: Evaluating Image Caption Using Vision-and-Language {BERT}",
    author = "Lee, Hwanhee  and
      Yoon, Seunghyun  and
      Dernoncourt, Franck  and
      Kim, Doo Soon  and
      Bui, Trung  and
      Jung, Kyomin",
    editor = "Eger, Steffen  and
      Gao, Yang  and
      Peyrard, Maxime  and
      Zhao, Wei  and
      Hovy, Eduard",
    booktitle = "Proceedings of the First Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/volume-fixes/2020.eval4nlp-1.4/",
    doi = "10.18653/v1/2020.eval4nlp-1.4",
    pages = "34--39"
}
@inproceedings{ethayarajh-sadigh-2020-bleu,
    title = "{BLEU} Neighbors: A Reference-less Approach to Automatic Evaluation",
    author = "Ethayarajh, Kawin  and
      Sadigh, Dorsa",
    editor = "Eger, Steffen  and
      Gao, Yang  and
      Peyrard, Maxime  and
      Zhao, Wei  and
      Hovy, Eduard",
    booktitle = "Proceedings of the First Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/volume-fixes/2020.eval4nlp-1.5/",
    doi = "10.18653/v1/2020.eval4nlp-1.5",
    pages = "40--50"
}
@inproceedings{chen-etal-2020-improving-text,
    title = "Improving Text Generation Evaluation with Batch Centering and Tempered Word Mover Distance",
    author = "Chen, Xi  and
      Ding, Nan  and
      Levinboim, Tomer  and
      Soricut, Radu",
    editor = "Eger, Steffen  and
      Gao, Yang  and
      Peyrard, Maxime  and
      Zhao, Wei  and
      Hovy, Eduard",
    booktitle = "Proceedings of the First Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/volume-fixes/2020.eval4nlp-1.6/",
    doi = "10.18653/v1/2020.eval4nlp-1.6",
    pages = "51--59"
}
@inproceedings{bremerman-etal-2020-evaluation,
    title = "On the Evaluation of Machine Translation n-best Lists",
    author = "Bremerman, Jacob  and
      Khayrallah, Huda  and
      Oard, Douglas  and
      Post, Matt",
    editor = "Eger, Steffen  and
      Gao, Yang  and
      Peyrard, Maxime  and
      Zhao, Wei  and
      Hovy, Eduard",
    booktitle = "Proceedings of the First Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/volume-fixes/2020.eval4nlp-1.7/",
    doi = "10.18653/v1/2020.eval4nlp-1.7",
    pages = "60--68"
}
@inproceedings{jha-etal-2020-artemis,
    title = "Artemis: A Novel Annotation Methodology for Indicative Single Document Summarization",
    author = "Jha, Rahul  and
      Bi, Keping  and
      Li, Yang  and
      Pakdaman, Mahdi  and
      Celikyilmaz, Asli  and
      Zhiboedov, Ivan  and
      McDonald, Kieran",
    editor = "Eger, Steffen  and
      Gao, Yang  and
      Peyrard, Maxime  and
      Zhao, Wei  and
      Hovy, Eduard",
    booktitle = "Proceedings of the First Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/volume-fixes/2020.eval4nlp-1.8/",
    doi = "10.18653/v1/2020.eval4nlp-1.8",
    pages = "69--78"
}
@inproceedings{yacouby-axman-2020-probabilistic,
    title = "Probabilistic Extension of Precision, Recall, and F1 Score for More Thorough Evaluation of Classification Models",
    author = "Yacouby, Reda  and
      Axman, Dustin",
    editor = "Eger, Steffen  and
      Gao, Yang  and
      Peyrard, Maxime  and
      Zhao, Wei  and
      Hovy, Eduard",
    booktitle = "Proceedings of the First Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/volume-fixes/2020.eval4nlp-1.9/",
    doi = "10.18653/v1/2020.eval4nlp-1.9",
    pages = "79--91"
}
@inproceedings{poliak-2020-survey,
    title = "A survey on Recognizing Textual Entailment as an {NLP} Evaluation",
    author = "Poliak, Adam",
    editor = "Eger, Steffen  and
      Gao, Yang  and
      Peyrard, Maxime  and
      Zhao, Wei  and
      Hovy, Eduard",
    booktitle = "Proceedings of the First Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/volume-fixes/2020.eval4nlp-1.10/",
    doi = "10.18653/v1/2020.eval4nlp-1.10",
    pages = "92--109"
}
@inproceedings{niu-penn-2020-grammaticality,
    title = "Grammaticality and Language Modelling",
    author = "Niu, Jingcheng  and
      Penn, Gerald",
    editor = "Eger, Steffen  and
      Gao, Yang  and
      Peyrard, Maxime  and
      Zhao, Wei  and
      Hovy, Eduard",
    booktitle = "Proceedings of the First Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/volume-fixes/2020.eval4nlp-1.11/",
    doi = "10.18653/v1/2020.eval4nlp-1.11",
    pages = "110--119"
}
@inproceedings{brink-andersen-etal-2020-one,
    title = "One of these words is not like the other: a reproduction of outlier identification using non-contextual word representations",
    author = "Brink Andersen, Jesper  and
      Bak Bertelsen, Mikkel  and
      H{\o}rby Schou, Mikkel  and
      Ciosici, Manuel R.  and
      Assent, Ira",
    editor = "Eger, Steffen  and
      Gao, Yang  and
      Peyrard, Maxime  and
      Zhao, Wei  and
      Hovy, Eduard",
    booktitle = "Proceedings of the First Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/volume-fixes/2020.eval4nlp-1.12/",
    doi = "10.18653/v1/2020.eval4nlp-1.12",
    pages = "120--130"
}
@inproceedings{dudy-bedrick-2020-words,
    title = "Are Some Words Worth More than Others?",
    author = "Dudy, Shiran  and
      Bedrick, Steven",
    editor = "Eger, Steffen  and
      Gao, Yang  and
      Peyrard, Maxime  and
      Zhao, Wei  and
      Hovy, Eduard",
    booktitle = "Proceedings of the First Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/volume-fixes/2020.eval4nlp-1.13/",
    doi = "10.18653/v1/2020.eval4nlp-1.13",
    pages = "131--142"
}
@inproceedings{gashteovski-etal-2020-aligning,
    title = "On Aligning {O}pen{IE} Extractions with Knowledge Bases: A Case Study",
    author = "Gashteovski, Kiril  and
      Gemulla, Rainer  and
      Kotnis, Bhushan  and
      Hertling, Sven  and
      Meilicke, Christian",
    editor = "Eger, Steffen  and
      Gao, Yang  and
      Peyrard, Maxime  and
      Zhao, Wei  and
      Hovy, Eduard",
    booktitle = "Proceedings of the First Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/volume-fixes/2020.eval4nlp-1.14/",
    doi = "10.18653/v1/2020.eval4nlp-1.14",
    pages = "143--154"
}
@inproceedings{wecker-etal-2020-clusterdatasplit,
    title = "{C}luster{D}ata{S}plit: Exploring Challenging Clustering-Based Data Splits for Model Performance Evaluation",
    author = "Wecker, Hanna  and
      Friedrich, Annemarie  and
      Adel, Heike",
    editor = "Eger, Steffen  and
      Gao, Yang  and
      Peyrard, Maxime  and
      Zhao, Wei  and
      Hovy, Eduard",
    booktitle = "Proceedings of the First Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/volume-fixes/2020.eval4nlp-1.15/",
    doi = "10.18653/v1/2020.eval4nlp-1.15",
    pages = "155--163"
}
@inproceedings{iskender-etal-2020-best,
    title = "Best Practices for Crowd-based Evaluation of {G}erman Summarization: Comparing Crowd, Expert and Automatic Evaluation",
    author = {Iskender, Neslihan  and
      Polzehl, Tim  and
      M{\"o}ller, Sebastian},
    editor = "Eger, Steffen  and
      Gao, Yang  and
      Peyrard, Maxime  and
      Zhao, Wei  and
      Hovy, Eduard",
    booktitle = "Proceedings of the First Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/volume-fixes/2020.eval4nlp-1.16/",
    doi = "10.18653/v1/2020.eval4nlp-1.16",
    pages = "164--175"
}
@inproceedings{stringham-izbicki-2020-evaluating,
    title = "Evaluating Word Embeddings on Low-Resource Languages",
    author = "Stringham, Nathan  and
      Izbicki, Mike",
    editor = "Eger, Steffen  and
      Gao, Yang  and
      Peyrard, Maxime  and
      Zhao, Wei  and
      Hovy, Eduard",
    booktitle = "Proceedings of the First Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/volume-fixes/2020.eval4nlp-1.17/",
    doi = "10.18653/v1/2020.eval4nlp-1.17",
    pages = "176--186"
}