<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="currey-heafield-2019-incorporating">
    <titleInfo>
        <title>Incorporating Source Syntax into Transformer-Based Neural Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Anna</namePart>
        <namePart type="family">Currey</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kenneth</namePart>
        <namePart type="family">Heafield</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-aug</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers)</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Florence, Italy</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Transformer-based neural machine translation (NMT) has recently achieved state-of-the-art performance on many machine translation tasks. However, recent work (Raganato and Tiedemann, 2018; Tang et al., 2018; Tran et al., 2018) has indicated that Transformer models may not learn syntactic structures as well as their recurrent neural network-based counterparts, particularly in low-resource cases. In this paper, we incorporate constituency parse information into a Transformer NMT model. We leverage linearized parses of the source training sentences in order to inject syntax into the Transformer architecture without modifying it. We introduce two methods: a multi-task machine translation and parsing model with a single encoder and decoder, and a mixed encoder model that learns to translate directly from parsed and unparsed source sentences. We evaluate our methods on low-resource translation from English into twenty target languages, showing consistent improvements of 1.3 BLEU on average across diverse target languages for the multi-task technique. We further evaluate the models on full-scale WMT tasks, finding that the multi-task model aids low- and medium-resource NMT but degenerates high-resource English-German translation.</abstract>
    <identifier type="citekey">currey-heafield-2019-incorporating</identifier>
    <identifier type="doi">10.18653/v1/W19-5203</identifier>
    <location>
        <url>https://aclanthology.org/W19-5203</url>
    </location>
    <part>
        <date>2019-aug</date>
        <extent unit="page">
            <start>24</start>
            <end>33</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Incorporating Source Syntax into Transformer-Based Neural Machine Translation
%A Currey, Anna
%A Heafield, Kenneth
%S Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers)
%D 2019
%8 aug
%I Association for Computational Linguistics
%C Florence, Italy
%F currey-heafield-2019-incorporating
%X Transformer-based neural machine translation (NMT) has recently achieved state-of-the-art performance on many machine translation tasks. However, recent work (Raganato and Tiedemann, 2018; Tang et al., 2018; Tran et al., 2018) has indicated that Transformer models may not learn syntactic structures as well as their recurrent neural network-based counterparts, particularly in low-resource cases. In this paper, we incorporate constituency parse information into a Transformer NMT model. We leverage linearized parses of the source training sentences in order to inject syntax into the Transformer architecture without modifying it. We introduce two methods: a multi-task machine translation and parsing model with a single encoder and decoder, and a mixed encoder model that learns to translate directly from parsed and unparsed source sentences. We evaluate our methods on low-resource translation from English into twenty target languages, showing consistent improvements of 1.3 BLEU on average across diverse target languages for the multi-task technique. We further evaluate the models on full-scale WMT tasks, finding that the multi-task model aids low- and medium-resource NMT but degenerates high-resource English-German translation.
%R 10.18653/v1/W19-5203
%U https://aclanthology.org/W19-5203
%U https://doi.org/10.18653/v1/W19-5203
%P 24-33

Markdown (Informal)

[Incorporating Source Syntax into Transformer-Based Neural Machine Translation](https://aclanthology.org/W19-5203) (Currey & Heafield, 2019)

• Incorporating Source Syntax into Transformer-Based Neural Machine Translation (Currey & Heafield, 2019)

ACL

• Anna Currey and Kenneth Heafield. 2019. Incorporating Source Syntax into Transformer-Based Neural Machine Translation. In Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers), pages 24–33, Florence, Italy. Association for Computational Linguistics.