@inproceedings{ma-etal-2019-improving,
title = "Improving Neural Machine Translation with Neural Syntactic Distance",
author = "Ma, Chunpeng and
Tamura, Akihiro and
Utiyama, Masao and
Sumita, Eiichiro and
Zhao, Tiejun",
editor = "Burstein, Jill and
Doran, Christy and
Solorio, Thamar",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1205",
doi = "10.18653/v1/N19-1205",
pages = "2032--2037",
abstract = "The explicit use of syntactic information has been proved useful for neural machine translation (NMT). However, previous methods resort to either tree-structured neural networks or long linearized sequences, both of which are inefficient. Neural syntactic distance (NSD) enables us to represent a constituent tree using a sequence whose length is identical to the number of words in the sentence. NSD has been used for constituent parsing, but not in machine translation. We propose five strategies to improve NMT with NSD. Experiments show that it is not trivial to improve NMT with NSD; however, the proposed strategies are shown to improve translation performance of the baseline model (+2.1 (En{--}Ja), +1.3 (Ja{--}En), +1.2 (En{--}Ch), and +1.0 (Ch{--}En) BLEU).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ma-etal-2019-improving">
<titleInfo>
<title>Improving Neural Machine Translation with Neural Syntactic Distance</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chunpeng</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akihiro</namePart>
<namePart type="family">Tamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masao</namePart>
<namePart type="family">Utiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eiichiro</namePart>
<namePart type="family">Sumita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tiejun</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christy</namePart>
<namePart type="family">Doran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The explicit use of syntactic information has been proved useful for neural machine translation (NMT). However, previous methods resort to either tree-structured neural networks or long linearized sequences, both of which are inefficient. Neural syntactic distance (NSD) enables us to represent a constituent tree using a sequence whose length is identical to the number of words in the sentence. NSD has been used for constituent parsing, but not in machine translation. We propose five strategies to improve NMT with NSD. Experiments show that it is not trivial to improve NMT with NSD; however, the proposed strategies are shown to improve translation performance of the baseline model (+2.1 (En–Ja), +1.3 (Ja–En), +1.2 (En–Ch), and +1.0 (Ch–En) BLEU).</abstract>
<identifier type="citekey">ma-etal-2019-improving</identifier>
<identifier type="doi">10.18653/v1/N19-1205</identifier>
<location>
<url>https://aclanthology.org/N19-1205</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>2032</start>
<end>2037</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Neural Machine Translation with Neural Syntactic Distance
%A Ma, Chunpeng
%A Tamura, Akihiro
%A Utiyama, Masao
%A Sumita, Eiichiro
%A Zhao, Tiejun
%Y Burstein, Jill
%Y Doran, Christy
%Y Solorio, Thamar
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F ma-etal-2019-improving
%X The explicit use of syntactic information has been proved useful for neural machine translation (NMT). However, previous methods resort to either tree-structured neural networks or long linearized sequences, both of which are inefficient. Neural syntactic distance (NSD) enables us to represent a constituent tree using a sequence whose length is identical to the number of words in the sentence. NSD has been used for constituent parsing, but not in machine translation. We propose five strategies to improve NMT with NSD. Experiments show that it is not trivial to improve NMT with NSD; however, the proposed strategies are shown to improve translation performance of the baseline model (+2.1 (En–Ja), +1.3 (Ja–En), +1.2 (En–Ch), and +1.0 (Ch–En) BLEU).
%R 10.18653/v1/N19-1205
%U https://aclanthology.org/N19-1205
%U https://doi.org/10.18653/v1/N19-1205
%P 2032-2037
Markdown (Informal)
[Improving Neural Machine Translation with Neural Syntactic Distance](https://aclanthology.org/N19-1205) (Ma et al., NAACL 2019)
ACL
- Chunpeng Ma, Akihiro Tamura, Masao Utiyama, Eiichiro Sumita, and Tiejun Zhao. 2019. Improving Neural Machine Translation with Neural Syntactic Distance. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 2032–2037, Minneapolis, Minnesota. Association for Computational Linguistics.