@inproceedings{mcdonald-chiang-2021-syntax,
title = "Syntax-Based Attention Masking for Neural Machine Translation",
author = "McDonald, Colin and
Chiang, David",
editor = "Durmus, Esin and
Gupta, Vivek and
Liu, Nelson and
Peng, Nanyun and
Su, Yu",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-srw.7",
doi = "10.18653/v1/2021.naacl-srw.7",
pages = "47--52",
abstract = "We present a simple method for extending transformers to source-side trees. We define a number of masks that limit self-attention based on relationships among tree nodes, and we allow each attention head to learn which mask or masks to use. On translation from English to various low-resource languages, and translation in both directions between English and German, our method always improves over simple linearization of the source-side parse tree and almost always improves over a sequence-to-sequence baseline, by up to +2.1 BLEU.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mcdonald-chiang-2021-syntax">
<titleInfo>
<title>Syntax-Based Attention Masking for Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Colin</namePart>
<namePart type="family">McDonald</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Chiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Esin</namePart>
<namePart type="family">Durmus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nelson</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nanyun</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Su</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>We present a simple method for extending transformers to source-side trees. We define a number of masks that limit self-attention based on relationships among tree nodes, and we allow each attention head to learn which mask or masks to use. On translation from English to various low-resource languages, and translation in both directions between English and German, our method always improves over simple linearization of the source-side parse tree and almost always improves over a sequence-to-sequence baseline, by up to +2.1 BLEU.</abstract>
<identifier type="citekey">mcdonald-chiang-2021-syntax</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-srw.7</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-srw.7</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>47</start>
<end>52</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Syntax-Based Attention Masking for Neural Machine Translation
%A McDonald, Colin
%A Chiang, David
%Y Durmus, Esin
%Y Gupta, Vivek
%Y Liu, Nelson
%Y Peng, Nanyun
%Y Su, Yu
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F mcdonald-chiang-2021-syntax
%X We present a simple method for extending transformers to source-side trees. We define a number of masks that limit self-attention based on relationships among tree nodes, and we allow each attention head to learn which mask or masks to use. On translation from English to various low-resource languages, and translation in both directions between English and German, our method always improves over simple linearization of the source-side parse tree and almost always improves over a sequence-to-sequence baseline, by up to +2.1 BLEU.
%R 10.18653/v1/2021.naacl-srw.7
%U https://aclanthology.org/2021.naacl-srw.7
%U https://doi.org/10.18653/v1/2021.naacl-srw.7
%P 47-52
Markdown (Informal)
[Syntax-Based Attention Masking for Neural Machine Translation](https://aclanthology.org/2021.naacl-srw.7) (McDonald & Chiang, NAACL 2021)
ACL
- Colin McDonald and David Chiang. 2021. Syntax-Based Attention Masking for Neural Machine Translation. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop, pages 47–52, Online. Association for Computational Linguistics.