<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhu-etal-2023-chain">
    <titleInfo>
        <title>Chain-of-Questions Training with Latent Answers for Robust Multistep Question Answering</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Wang</namePart>
        <namePart type="family">Zhu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jesse</namePart>
        <namePart type="family">Thomason</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Robin</namePart>
        <namePart type="family">Jia</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Houda</namePart>
            <namePart type="family">Bouamor</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Juan</namePart>
            <namePart type="family">Pino</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kalika</namePart>
            <namePart type="family">Bali</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Singapore</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We propose Chain-of-Questions, a framework that trains a model to robustly answer multistep questions by generating and answering sub-questions. We obtain supervision for sub-questions from human-annotated question decomposition meaning representation (QDMR), but QDMR does not include annotated answers to sub-questions. To overcome this technical challenge, we treat sub-answers as latent variables and infer them with a novel dynamic mixture of Hard-EM and MAPO. Chain-of-Questions is effective and robust, greatly outperforming strong neuro-symbolic methods by 9.0 F1 on a DROP contrast set and GPT-3.5 by 24.3 F1 on a HotpotQA adversarial set.</abstract>
    <identifier type="citekey">zhu-etal-2023-chain</identifier>
    <identifier type="doi">10.18653/v1/2023.emnlp-main.547</identifier>
    <location>
        <url>https://aclanthology.org/2023.emnlp-main.547</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>8845</start>
            <end>8860</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Chain-of-Questions Training with Latent Answers for Robust Multistep Question Answering
%A Zhu, Wang
%A Thomason, Jesse
%A Jia, Robin
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F zhu-etal-2023-chain
%X We propose Chain-of-Questions, a framework that trains a model to robustly answer multistep questions by generating and answering sub-questions. We obtain supervision for sub-questions from human-annotated question decomposition meaning representation (QDMR), but QDMR does not include annotated answers to sub-questions. To overcome this technical challenge, we treat sub-answers as latent variables and infer them with a novel dynamic mixture of Hard-EM and MAPO. Chain-of-Questions is effective and robust, greatly outperforming strong neuro-symbolic methods by 9.0 F1 on a DROP contrast set and GPT-3.5 by 24.3 F1 on a HotpotQA adversarial set.
%R 10.18653/v1/2023.emnlp-main.547
%U https://aclanthology.org/2023.emnlp-main.547
%U https://doi.org/10.18653/v1/2023.emnlp-main.547
%P 8845-8860

Markdown (Informal)

[Chain-of-Questions Training with Latent Answers for Robust Multistep Question Answering](https://aclanthology.org/2023.emnlp-main.547) (Zhu et al., EMNLP 2023)

• Chain-of-Questions Training with Latent Answers for Robust Multistep Question Answering (Zhu et al., EMNLP 2023)

ACL

• Wang Zhu, Jesse Thomason, and Robin Jia. 2023. Chain-of-Questions Training with Latent Answers for Robust Multistep Question Answering. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 8845–8860, Singapore. Association for Computational Linguistics.