<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2020-accurate">
    <titleInfo>
        <title>Accurate Word Alignment Induction from Neural Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yun</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yang</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Guanhua</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xin</namePart>
        <namePart type="family">Jiang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Qun</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Despite its original goal to jointly learn to align and translate, prior researches suggest that Transformer captures poor word alignments through its attention mechanism. In this paper, we show that attention weights do capture accurate word alignments and propose two novel word alignment induction methods Shift-Att and Shift-AET. The main idea is to induce alignments at the step when the to-be-aligned target token is the decoder input rather than the decoder output as in previous work. Shift-Att is an interpretation method that induces alignments from the attention weights of Transformer and does not require parameter update or architecture change. Shift-AET extracts alignments from an additional alignment module which is tightly integrated into Transformer and trained in isolation with supervision from symmetrized Shift-Att alignments. Experiments on three publicly available datasets demonstrate that both methods perform better than their corresponding neural baselines and Shift-AET significantly outperforms GIZA++ by 1.4-4.8 AER points.</abstract>
    <identifier type="citekey">chen-etal-2020-accurate</identifier>
    <identifier type="doi">10.18653/v1/2020.emnlp-main.42</identifier>
    <location>
        <url>https://aclanthology.org/2020.emnlp-main.42</url>
    </location>
    <part>
        <date>2020-11</date>
        <extent unit="page">
            <start>566</start>
            <end>576</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Accurate Word Alignment Induction from Neural Machine Translation
%A Chen, Yun
%A Liu, Yang
%A Chen, Guanhua
%A Jiang, Xin
%A Liu, Qun
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F chen-etal-2020-accurate
%X Despite its original goal to jointly learn to align and translate, prior researches suggest that Transformer captures poor word alignments through its attention mechanism. In this paper, we show that attention weights do capture accurate word alignments and propose two novel word alignment induction methods Shift-Att and Shift-AET. The main idea is to induce alignments at the step when the to-be-aligned target token is the decoder input rather than the decoder output as in previous work. Shift-Att is an interpretation method that induces alignments from the attention weights of Transformer and does not require parameter update or architecture change. Shift-AET extracts alignments from an additional alignment module which is tightly integrated into Transformer and trained in isolation with supervision from symmetrized Shift-Att alignments. Experiments on three publicly available datasets demonstrate that both methods perform better than their corresponding neural baselines and Shift-AET significantly outperforms GIZA++ by 1.4-4.8 AER points.
%R 10.18653/v1/2020.emnlp-main.42
%U https://aclanthology.org/2020.emnlp-main.42
%U https://doi.org/10.18653/v1/2020.emnlp-main.42
%P 566-576

Markdown (Informal)

[Accurate Word Alignment Induction from Neural Machine Translation](https://aclanthology.org/2020.emnlp-main.42) (Chen et al., EMNLP 2020)

• Accurate Word Alignment Induction from Neural Machine Translation (Chen et al., EMNLP 2020)

ACL

• Yun Chen, Yang Liu, Guanhua Chen, Xin Jiang, and Qun Liu. 2020. Accurate Word Alignment Induction from Neural Machine Translation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 566–576, Online. Association for Computational Linguistics.