<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="du-ji-2022-retrieval">
    <titleInfo>
        <title>Retrieval-Augmented Generative Question Answering for Event Argument Extraction</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Xinya</namePart>
        <namePart type="family">Du</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Heng</namePart>
        <namePart type="family">Ji</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 2022 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yoav</namePart>
            <namePart type="family">Goldberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zornitsa</namePart>
            <namePart type="family">Kozareva</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</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</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Event argument extraction has long been studied as a sequential prediction problem with extractive-based methods, tackling each argument in isolation. Although recent work proposes generation-based methods to capture cross-argument dependency, they require generating and post-processing a complicated target sequence (template). Motivated by these observations and recent pretrained language models’ capabilities of learning from demonstrations. We propose a retrieval-augmented generative QA model (R-GQA) for event argument extraction. It retrieves the most similar QA pair and augments it as prompt to the current example’s context, then decodes the arguments as answers. Our approach outperforms substantially prior methods across various settings (i.e. fully supervised, domain transfer, and fewshot learning). Finally, we propose a clustering-based sampling strategy (JointEnc) and conduct a thorough analysis of how different strategies influence the few-shot learning performances.</abstract>
    <identifier type="citekey">du-ji-2022-retrieval</identifier>
    <identifier type="doi">10.18653/v1/2022.emnlp-main.307</identifier>
    <location>
        <url>https://aclanthology.org/2022.emnlp-main.307</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>4649</start>
            <end>4666</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Retrieval-Augmented Generative Question Answering for Event Argument Extraction
%A Du, Xinya
%A Ji, Heng
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F du-ji-2022-retrieval
%X Event argument extraction has long been studied as a sequential prediction problem with extractive-based methods, tackling each argument in isolation. Although recent work proposes generation-based methods to capture cross-argument dependency, they require generating and post-processing a complicated target sequence (template). Motivated by these observations and recent pretrained language models’ capabilities of learning from demonstrations. We propose a retrieval-augmented generative QA model (R-GQA) for event argument extraction. It retrieves the most similar QA pair and augments it as prompt to the current example’s context, then decodes the arguments as answers. Our approach outperforms substantially prior methods across various settings (i.e. fully supervised, domain transfer, and fewshot learning). Finally, we propose a clustering-based sampling strategy (JointEnc) and conduct a thorough analysis of how different strategies influence the few-shot learning performances.
%R 10.18653/v1/2022.emnlp-main.307
%U https://aclanthology.org/2022.emnlp-main.307
%U https://doi.org/10.18653/v1/2022.emnlp-main.307
%P 4649-4666

Markdown (Informal)

[Retrieval-Augmented Generative Question Answering for Event Argument Extraction](https://aclanthology.org/2022.emnlp-main.307) (Du & Ji, EMNLP 2022)

• Retrieval-Augmented Generative Question Answering for Event Argument Extraction (Du & Ji, EMNLP 2022)

ACL

• Xinya Du and Heng Ji. 2022. Retrieval-Augmented Generative Question Answering for Event Argument Extraction. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 4649–4666, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.