<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-su-2021-fast">
    <titleInfo>
        <title>How Fast can BERT Learn Simple Natural Language Inference?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yi-Chung</namePart>
        <namePart type="family">Lin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Keh-Yih</namePart>
        <namePart type="family">Su</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-04</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Paola</namePart>
            <namePart type="family">Merlo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jorg</namePart>
            <namePart type="family">Tiedemann</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Reut</namePart>
            <namePart type="family">Tsarfaty</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper empirically studies whether BERT can really learn to conduct natural language inference (NLI) without utilizing hidden dataset bias; and how efficiently it can learn if it could. This is done via creating a simple entailment judgment case which involves only binary predicates in plain English. The results show that the learning process of BERT is very slow. However, the efficiency of learning can be greatly improved (data reduction by a factor of 1,500) if task-related features are added. This suggests that domain knowledge greatly helps when conducting NLI with neural networks.</abstract>
    <identifier type="citekey">lin-su-2021-fast</identifier>
    <identifier type="doi">10.18653/v1/2021.eacl-main.51</identifier>
    <location>
        <url>https://aclanthology.org/2021.eacl-main.51</url>
    </location>
    <part>
        <date>2021-04</date>
        <extent unit="page">
            <start>626</start>
            <end>633</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T How Fast can BERT Learn Simple Natural Language Inference?
%A Lin, Yi-Chung
%A Su, Keh-Yih
%Y Merlo, Paola
%Y Tiedemann, Jorg
%Y Tsarfaty, Reut
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F lin-su-2021-fast
%X This paper empirically studies whether BERT can really learn to conduct natural language inference (NLI) without utilizing hidden dataset bias; and how efficiently it can learn if it could. This is done via creating a simple entailment judgment case which involves only binary predicates in plain English. The results show that the learning process of BERT is very slow. However, the efficiency of learning can be greatly improved (data reduction by a factor of 1,500) if task-related features are added. This suggests that domain knowledge greatly helps when conducting NLI with neural networks.
%R 10.18653/v1/2021.eacl-main.51
%U https://aclanthology.org/2021.eacl-main.51
%U https://doi.org/10.18653/v1/2021.eacl-main.51
%P 626-633

Markdown (Informal)

[How Fast can BERT Learn Simple Natural Language Inference?](https://aclanthology.org/2021.eacl-main.51) (Lin & Su, EACL 2021)

• How Fast can BERT Learn Simple Natural Language Inference? (Lin & Su, EACL 2021)

ACL

• Yi-Chung Lin and Keh-Yih Su. 2021. How Fast can BERT Learn Simple Natural Language Inference?. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 626–633, Online. Association for Computational Linguistics.