@inproceedings{rakshit-flanigan-2022-figurativeqa,
title = "{F}igurative{QA}: A Test Benchmark for Figurativeness Comprehension for Question Answering",
author = "Rakshit, Geetanjali and
Flanigan, Jeffrey",
editor = "Ghosh, Debanjan and
Beigman Klebanov, Beata and
Muresan, Smaranda and
Feldman, Anna and
Poria, Soujanya and
Chakrabarty, Tuhin",
booktitle = "Proceedings of the 3rd Workshop on Figurative Language Processing (FLP)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.flp-1.23",
doi = "10.18653/v1/2022.flp-1.23",
pages = "160--166",
abstract = "Figurative language is widespread in human language (Lakoff and Johnson, 2008) posing potential challenges in NLP applications. In this paper, we investigate the effect of figurative language on the task of question answering (QA). We construct FigQA, a test set of 400 yes-no questions with figurative and non-figurative contexts, extracted from product reviews and restaurant reviews. We demonstrate that a state-of-the-art RoBERTa QA model has considerably lower performance in question answering when the contexts are figurative rather than literal, indicating a gap in current models. We propose a general method for improving the performance of QA models by converting the figurative contexts into non-figurative by prompting GPT-3, and demonstrate its effectiveness. Our results indicate a need for building QA models infused with figurative language understanding capabilities.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rakshit-flanigan-2022-figurativeqa">
<titleInfo>
<title>FigurativeQA: A Test Benchmark for Figurativeness Comprehension for Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Geetanjali</namePart>
<namePart type="family">Rakshit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeffrey</namePart>
<namePart type="family">Flanigan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on Figurative Language Processing (FLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Beata</namePart>
<namePart type="family">Beigman Klebanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Feldman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soujanya</namePart>
<namePart type="family">Poria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tuhin</namePart>
<namePart type="family">Chakrabarty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Figurative language is widespread in human language (Lakoff and Johnson, 2008) posing potential challenges in NLP applications. In this paper, we investigate the effect of figurative language on the task of question answering (QA). We construct FigQA, a test set of 400 yes-no questions with figurative and non-figurative contexts, extracted from product reviews and restaurant reviews. We demonstrate that a state-of-the-art RoBERTa QA model has considerably lower performance in question answering when the contexts are figurative rather than literal, indicating a gap in current models. We propose a general method for improving the performance of QA models by converting the figurative contexts into non-figurative by prompting GPT-3, and demonstrate its effectiveness. Our results indicate a need for building QA models infused with figurative language understanding capabilities.</abstract>
<identifier type="citekey">rakshit-flanigan-2022-figurativeqa</identifier>
<identifier type="doi">10.18653/v1/2022.flp-1.23</identifier>
<location>
<url>https://aclanthology.org/2022.flp-1.23</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>160</start>
<end>166</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FigurativeQA: A Test Benchmark for Figurativeness Comprehension for Question Answering
%A Rakshit, Geetanjali
%A Flanigan, Jeffrey
%Y Ghosh, Debanjan
%Y Beigman Klebanov, Beata
%Y Muresan, Smaranda
%Y Feldman, Anna
%Y Poria, Soujanya
%Y Chakrabarty, Tuhin
%S Proceedings of the 3rd Workshop on Figurative Language Processing (FLP)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F rakshit-flanigan-2022-figurativeqa
%X Figurative language is widespread in human language (Lakoff and Johnson, 2008) posing potential challenges in NLP applications. In this paper, we investigate the effect of figurative language on the task of question answering (QA). We construct FigQA, a test set of 400 yes-no questions with figurative and non-figurative contexts, extracted from product reviews and restaurant reviews. We demonstrate that a state-of-the-art RoBERTa QA model has considerably lower performance in question answering when the contexts are figurative rather than literal, indicating a gap in current models. We propose a general method for improving the performance of QA models by converting the figurative contexts into non-figurative by prompting GPT-3, and demonstrate its effectiveness. Our results indicate a need for building QA models infused with figurative language understanding capabilities.
%R 10.18653/v1/2022.flp-1.23
%U https://aclanthology.org/2022.flp-1.23
%U https://doi.org/10.18653/v1/2022.flp-1.23
%P 160-166
Markdown (Informal)
[FigurativeQA: A Test Benchmark for Figurativeness Comprehension for Question Answering](https://aclanthology.org/2022.flp-1.23) (Rakshit & Flanigan, Fig-Lang 2022)
ACL