@inproceedings{currey-heafield-2019-incorporating,
title = "Incorporating Source Syntax into Transformer-Based Neural Machine Translation",
author = "Currey, Anna and
Heafield, Kenneth",
editor = "Bojar, Ond{\v{r}}ej and
Chatterjee, Rajen and
Federmann, Christian and
Fishel, Mark and
Graham, Yvette and
Haddow, Barry and
Huck, Matthias and
Yepes, Antonio Jimeno and
Koehn, Philipp and
Martins, Andr{\'e} and
Monz, Christof and
Negri, Matteo and
N{\'e}v{\'e}ol, Aur{\'e}lie and
Neves, Mariana and
Post, Matt and
Turchi, Marco and
Verspoor, Karin",
booktitle = "Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers)",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-5203",
doi = "10.18653/v1/W19-5203",
pages = "24--33",
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.",
}
<?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>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Bojar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajen</namePart>
<namePart type="family">Chatterjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Federmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Fishel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Huck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="given">Jimeno</namePart>
<namePart type="family">Yepes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aurélie</namePart>
<namePart type="family">Névéol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mariana</namePart>
<namePart type="family">Neves</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matt</namePart>
<namePart type="family">Post</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Turchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karin</namePart>
<namePart type="family">Verspoor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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>2019-08</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
%Y Bojar, Ondřej
%Y Chatterjee, Rajen
%Y Federmann, Christian
%Y Fishel, Mark
%Y Graham, Yvette
%Y Haddow, Barry
%Y Huck, Matthias
%Y Yepes, Antonio Jimeno
%Y Koehn, Philipp
%Y Martins, André
%Y Monz, Christof
%Y Negri, Matteo
%Y Névéol, Aurélie
%Y Neves, Mariana
%Y Post, Matt
%Y Turchi, Marco
%Y Verspoor, Karin
%S Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers)
%D 2019
%8 August
%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, WMT 2019)
ACL