@inproceedings{aoyama-etal-2023-gentle,
title = "{GENTLE}: A Genre-Diverse Multilayer Challenge Set for {E}nglish {NLP} and Linguistic Evaluation",
author = "Aoyama, Tatsuya and
Behzad, Shabnam and
Gessler, Luke and
Levine, Lauren and
Lin, Jessica and
Liu, Yang Janet and
Peng, Siyao and
Zhu, Yilun and
Zeldes, Amir",
editor = "Prange, Jakob and
Friedrich, Annemarie",
booktitle = "Proceedings of the 17th Linguistic Annotation Workshop (LAW-XVII)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.law-1.17",
doi = "10.18653/v1/2023.law-1.17",
pages = "166--178",
abstract = "We present GENTLE, a new mixed-genre English challenge corpus totaling 17K tokens and consisting of 8 unusual text types for out-of-domain evaluation: dictionary entries, esports commentaries, legal documents, medical notes, poetry, mathematical proofs, syllabuses, and threat letters. GENTLE is manually annotated for a variety of popular NLP tasks, including syntactic dependency parsing, entity recognition, coreference resolution, and discourse parsing. We evaluate state-of-the-art NLP systems on GENTLE and find severe degradation for at least some genres in their performance on all tasks, which indicates GENTLE{'}s utility as an evaluation dataset for NLP systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aoyama-etal-2023-gentle">
<titleInfo>
<title>GENTLE: A Genre-Diverse Multilayer Challenge Set for English NLP and Linguistic Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tatsuya</namePart>
<namePart type="family">Aoyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shabnam</namePart>
<namePart type="family">Behzad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Gessler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lauren</namePart>
<namePart type="family">Levine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessica</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="given">Janet</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siyao</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yilun</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Zeldes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Linguistic Annotation Workshop (LAW-XVII)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jakob</namePart>
<namePart type="family">Prange</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annemarie</namePart>
<namePart type="family">Friedrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present GENTLE, a new mixed-genre English challenge corpus totaling 17K tokens and consisting of 8 unusual text types for out-of-domain evaluation: dictionary entries, esports commentaries, legal documents, medical notes, poetry, mathematical proofs, syllabuses, and threat letters. GENTLE is manually annotated for a variety of popular NLP tasks, including syntactic dependency parsing, entity recognition, coreference resolution, and discourse parsing. We evaluate state-of-the-art NLP systems on GENTLE and find severe degradation for at least some genres in their performance on all tasks, which indicates GENTLE’s utility as an evaluation dataset for NLP systems.</abstract>
<identifier type="citekey">aoyama-etal-2023-gentle</identifier>
<identifier type="doi">10.18653/v1/2023.law-1.17</identifier>
<location>
<url>https://aclanthology.org/2023.law-1.17</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>166</start>
<end>178</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GENTLE: A Genre-Diverse Multilayer Challenge Set for English NLP and Linguistic Evaluation
%A Aoyama, Tatsuya
%A Behzad, Shabnam
%A Gessler, Luke
%A Levine, Lauren
%A Lin, Jessica
%A Liu, Yang Janet
%A Peng, Siyao
%A Zhu, Yilun
%A Zeldes, Amir
%Y Prange, Jakob
%Y Friedrich, Annemarie
%S Proceedings of the 17th Linguistic Annotation Workshop (LAW-XVII)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F aoyama-etal-2023-gentle
%X We present GENTLE, a new mixed-genre English challenge corpus totaling 17K tokens and consisting of 8 unusual text types for out-of-domain evaluation: dictionary entries, esports commentaries, legal documents, medical notes, poetry, mathematical proofs, syllabuses, and threat letters. GENTLE is manually annotated for a variety of popular NLP tasks, including syntactic dependency parsing, entity recognition, coreference resolution, and discourse parsing. We evaluate state-of-the-art NLP systems on GENTLE and find severe degradation for at least some genres in their performance on all tasks, which indicates GENTLE’s utility as an evaluation dataset for NLP systems.
%R 10.18653/v1/2023.law-1.17
%U https://aclanthology.org/2023.law-1.17
%U https://doi.org/10.18653/v1/2023.law-1.17
%P 166-178
Markdown (Informal)
[GENTLE: A Genre-Diverse Multilayer Challenge Set for English NLP and Linguistic Evaluation](https://aclanthology.org/2023.law-1.17) (Aoyama et al., LAW 2023)
ACL
- Tatsuya Aoyama, Shabnam Behzad, Luke Gessler, Lauren Levine, Jessica Lin, Yang Janet Liu, Siyao Peng, Yilun Zhu, and Amir Zeldes. 2023. GENTLE: A Genre-Diverse Multilayer Challenge Set for English NLP and Linguistic Evaluation. In Proceedings of the 17th Linguistic Annotation Workshop (LAW-XVII), pages 166–178, Toronto, Canada. Association for Computational Linguistics.