<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rakshit-flanigan-2023-sinfully">
    <titleInfo>
        <title>Does the “Most Sinfully Decadent Cake Ever” Taste Good? Answering Yes/No Questions from Figurative Contexts</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>2023-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ruslan</namePart>
            <namePart type="family">Mitkov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Galia</namePart>
            <namePart type="family">Angelova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
            <place>
                <placeTerm type="text">Varna, Bulgaria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Figurative language is commonplace in natural language, and while making communication memorable and creative, can be difficult to understand. In this work, we investigate the robustness of Question Answering (QA) models on figurative text. Yes/no questions, in particular, are a useful probe of figurative language understanding capabilities of large language models. We propose FigurativeQA, a set of 1000 yes/no questions with figurative and non-figurative contexts, extracted from the domains of restaurant and product reviews. We show that state-of-the-art BERT-based QA models exhibit an average performance drop of up to 15% points when answering questions from figurative contexts, as compared to non-figurative ones. While models like GPT-3 and ChatGPT are better at handling figurative texts, we show that further performance gains can be achieved by automatically simplifying the figurative contexts into their non-figurative (literal) counterparts. We find that the best overall model is ChatGPT with chain-of-thought prompting to generate non-figurative contexts. Our work provides a promising direction for building more robust QA models with figurative language understanding capabilities.</abstract>
    <identifier type="citekey">rakshit-flanigan-2023-sinfully</identifier>
    <location>
        <url>https://aclanthology.org/2023.ranlp-1.100</url>
    </location>
    <part>
        <date>2023-09</date>
        <extent unit="page">
            <start>926</start>
            <end>936</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Does the “Most Sinfully Decadent Cake Ever” Taste Good? Answering Yes/No Questions from Figurative Contexts
%A Rakshit, Geetanjali
%A Flanigan, Jeffrey
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing
%D 2023
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F rakshit-flanigan-2023-sinfully
%X Figurative language is commonplace in natural language, and while making communication memorable and creative, can be difficult to understand. In this work, we investigate the robustness of Question Answering (QA) models on figurative text. Yes/no questions, in particular, are a useful probe of figurative language understanding capabilities of large language models. We propose FigurativeQA, a set of 1000 yes/no questions with figurative and non-figurative contexts, extracted from the domains of restaurant and product reviews. We show that state-of-the-art BERT-based QA models exhibit an average performance drop of up to 15% points when answering questions from figurative contexts, as compared to non-figurative ones. While models like GPT-3 and ChatGPT are better at handling figurative texts, we show that further performance gains can be achieved by automatically simplifying the figurative contexts into their non-figurative (literal) counterparts. We find that the best overall model is ChatGPT with chain-of-thought prompting to generate non-figurative contexts. Our work provides a promising direction for building more robust QA models with figurative language understanding capabilities.
%U https://aclanthology.org/2023.ranlp-1.100
%P 926-936

Markdown (Informal)

[Does the “Most Sinfully Decadent Cake Ever” Taste Good? Answering Yes/No Questions from Figurative Contexts](https://aclanthology.org/2023.ranlp-1.100) (Rakshit & Flanigan, RANLP 2023)

• Does the “Most Sinfully Decadent Cake Ever” Taste Good? Answering Yes/No Questions from Figurative Contexts (Rakshit & Flanigan, RANLP 2023)

ACL

• Geetanjali Rakshit and Jeffrey Flanigan. 2023. Does the “Most Sinfully Decadent Cake Ever” Taste Good? Answering Yes/No Questions from Figurative Contexts. In Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing, pages 926–936, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.