<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="di-liello-etal-2023-context">
    <titleInfo>
        <title>Context-Aware Transformer Pre-Training for Answer Sentence Selection</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Luca</namePart>
        <namePart type="family">Di Liello</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Siddhant</namePart>
        <namePart type="family">Garg</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alessandro</namePart>
        <namePart type="family">Moschitti</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 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Rogers</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jordan</namePart>
            <namePart type="family">Boyd-Graber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Naoaki</namePart>
            <namePart type="family">Okazaki</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>Answer Sentence Selection (AS2) is a core component for building an accurate Question Answering pipeline. AS2 models rank a set of candidate sentences based on how likely they answer a given question. The state of the art in AS2 exploits pre-trained transformers by transferring them on large annotated datasets, while using local contextual information around the candidate sentence. In this paper, we propose three pre-training objectives designed to mimic the downstream fine-tuning task of contextual AS2. This allows for specializing LMs when fine-tuning for contextual AS2. Our experiments on three public and two large-scale industrial datasets show that our pre-training approaches (applied to RoBERTa and ELECTRA) can improve baseline contextual AS2 accuracy by up to 8% on some datasets.</abstract>
    <identifier type="citekey">di-liello-etal-2023-context</identifier>
    <identifier type="doi">10.18653/v1/2023.acl-short.40</identifier>
    <location>
        <url>https://aclanthology.org/2023.acl-short.40</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>458</start>
            <end>468</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Context-Aware Transformer Pre-Training for Answer Sentence Selection
%A Di Liello, Luca
%A Garg, Siddhant
%A Moschitti, Alessandro
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F di-liello-etal-2023-context
%X Answer Sentence Selection (AS2) is a core component for building an accurate Question Answering pipeline. AS2 models rank a set of candidate sentences based on how likely they answer a given question. The state of the art in AS2 exploits pre-trained transformers by transferring them on large annotated datasets, while using local contextual information around the candidate sentence. In this paper, we propose three pre-training objectives designed to mimic the downstream fine-tuning task of contextual AS2. This allows for specializing LMs when fine-tuning for contextual AS2. Our experiments on three public and two large-scale industrial datasets show that our pre-training approaches (applied to RoBERTa and ELECTRA) can improve baseline contextual AS2 accuracy by up to 8% on some datasets.
%R 10.18653/v1/2023.acl-short.40
%U https://aclanthology.org/2023.acl-short.40
%U https://doi.org/10.18653/v1/2023.acl-short.40
%P 458-468

Markdown (Informal)

[Context-Aware Transformer Pre-Training for Answer Sentence Selection](https://aclanthology.org/2023.acl-short.40) (Di Liello et al., ACL 2023)

• Context-Aware Transformer Pre-Training for Answer Sentence Selection (Di Liello et al., ACL 2023)

ACL

• Luca Di Liello, Siddhant Garg, and Alessandro Moschitti. 2023. Context-Aware Transformer Pre-Training for Answer Sentence Selection. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 458–468, Toronto, Canada. Association for Computational Linguistics.