<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mulang-etal-2020-fine">
    <titleInfo>
        <title>Fine-tuning BERT with Focus Words for Explanation Regeneration</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Isaiah</namePart>
        <namePart type="given">Onando</namePart>
        <namePart type="family">Mulang’</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jennifer</namePart>
        <namePart type="family">D’Souza</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sören</namePart>
        <namePart type="family">Auer</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Ninth Joint Conference on Lexical and Computational Semantics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Iryna</namePart>
            <namePart type="family">Gurevych</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marianna</namePart>
            <namePart type="family">Apidianaki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Manaal</namePart>
            <namePart type="family">Faruqui</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Explanation generation introduced as the world tree corpus (Jansen et al., 2018) is an emerging NLP task involving multi-hop inference for explaining the correct answer in multiple-choice QA. It is a challenging task evidenced by low state-of-the-art performances(below 60% in F-score) demonstrated on the task. Of the state-of-the-art approaches, fine-tuned transformer-based (Vaswani et al., 2017) BERT models have shown great promise toward continued system performance improvements compared with approaches relying on surface-level cues alone that demonstrate performance saturation. In this work, we take a novel direction by addressing a particular linguistic characteristic of the data — we introduce a novel and lightweight focus feature in the transformer-based model and examine task improvements. Our evaluations reveal a significantly positive impact of this lightweight focus feature achieving the highest scores, second only to a significantly computationally intensive system.</abstract>
    <identifier type="citekey">mulang-etal-2020-fine</identifier>
    <location>
        <url>https://aclanthology.org/2020.starsem-1.13</url>
    </location>
    <part>
        <date>2020-12</date>
        <extent unit="page">
            <start>125</start>
            <end>130</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Fine-tuning BERT with Focus Words for Explanation Regeneration
%A Mulang’, Isaiah Onando
%A D’Souza, Jennifer
%A Auer, Sören
%Y Gurevych, Iryna
%Y Apidianaki, Marianna
%Y Faruqui, Manaal
%S Proceedings of the Ninth Joint Conference on Lexical and Computational Semantics
%D 2020
%8 December
%I Association for Computational Linguistics
%C Barcelona, Spain (Online)
%F mulang-etal-2020-fine
%X Explanation generation introduced as the world tree corpus (Jansen et al., 2018) is an emerging NLP task involving multi-hop inference for explaining the correct answer in multiple-choice QA. It is a challenging task evidenced by low state-of-the-art performances(below 60% in F-score) demonstrated on the task. Of the state-of-the-art approaches, fine-tuned transformer-based (Vaswani et al., 2017) BERT models have shown great promise toward continued system performance improvements compared with approaches relying on surface-level cues alone that demonstrate performance saturation. In this work, we take a novel direction by addressing a particular linguistic characteristic of the data — we introduce a novel and lightweight focus feature in the transformer-based model and examine task improvements. Our evaluations reveal a significantly positive impact of this lightweight focus feature achieving the highest scores, second only to a significantly computationally intensive system.
%U https://aclanthology.org/2020.starsem-1.13
%P 125-130

Markdown (Informal)

[Fine-tuning BERT with Focus Words for Explanation Regeneration](https://aclanthology.org/2020.starsem-1.13) (Mulang’ et al., *SEM 2020)

• Fine-tuning BERT with Focus Words for Explanation Regeneration (Mulang’ et al., *SEM 2020)

ACL

• Isaiah Onando Mulang’, Jennifer D’Souza, and Sören Auer. 2020. Fine-tuning BERT with Focus Words for Explanation Regeneration. In Proceedings of the Ninth Joint Conference on Lexical and Computational Semantics, pages 125–130, Barcelona, Spain (Online). Association for Computational Linguistics.