@inproceedings{chen-etal-2018-combining,
title = "Combining Character and Word Information in Neural Machine Translation Using a Multi-Level Attention",
author = "Chen, Huadong and
Huang, Shujian and
Chiang, David and
Dai, Xinyu and
Chen, Jiajun",
editor = "Walker, Marilyn and
Ji, Heng and
Stent, Amanda",
booktitle = "Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)",
month = jun,
year = "2018",
address = "New Orleans, Louisiana",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N18-1116/",
doi = "10.18653/v1/N18-1116",
pages = "1284--1293",
abstract = "Natural language sentences, being hierarchical, can be represented at different levels of granularity, like words, subwords, or characters. But most neural machine translation systems require the sentence to be represented as a sequence at a single level of granularity. It can be difficult to determine which granularity is better for a particular translation task. In this paper, we improve the model by incorporating multiple levels of granularity. Specifically, we propose (1) an encoder with character attention which augments the (sub)word-level representation with character-level information; (2) a decoder with multiple attentions that enable the representations from different levels of granularity to control the translation cooperatively. Experiments on three translation tasks demonstrate that our proposed models outperform the standard word-based model, the subword-based model, and a strong character-based model."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2018-combining">
<titleInfo>
<title>Combining Character and Word Information in Neural Machine Translation Using a Multi-Level Attention</title>
</titleInfo>
<name type="personal">
<namePart type="given">Huadong</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shujian</namePart>
<namePart type="family">Huang</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>
<name type="personal">
<namePart type="given">Xinyu</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marilyn</namePart>
<namePart type="family">Walker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amanda</namePart>
<namePart type="family">Stent</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">New Orleans, Louisiana</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Natural language sentences, being hierarchical, can be represented at different levels of granularity, like words, subwords, or characters. But most neural machine translation systems require the sentence to be represented as a sequence at a single level of granularity. It can be difficult to determine which granularity is better for a particular translation task. In this paper, we improve the model by incorporating multiple levels of granularity. Specifically, we propose (1) an encoder with character attention which augments the (sub)word-level representation with character-level information; (2) a decoder with multiple attentions that enable the representations from different levels of granularity to control the translation cooperatively. Experiments on three translation tasks demonstrate that our proposed models outperform the standard word-based model, the subword-based model, and a strong character-based model.</abstract>
<identifier type="citekey">chen-etal-2018-combining</identifier>
<identifier type="doi">10.18653/v1/N18-1116</identifier>
<location>
<url>https://aclanthology.org/N18-1116/</url>
</location>
<part>
<date>2018-06</date>
<extent unit="page">
<start>1284</start>
<end>1293</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Combining Character and Word Information in Neural Machine Translation Using a Multi-Level Attention
%A Chen, Huadong
%A Huang, Shujian
%A Chiang, David
%A Dai, Xinyu
%A Chen, Jiajun
%Y Walker, Marilyn
%Y Ji, Heng
%Y Stent, Amanda
%S Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)
%D 2018
%8 June
%I Association for Computational Linguistics
%C New Orleans, Louisiana
%F chen-etal-2018-combining
%X Natural language sentences, being hierarchical, can be represented at different levels of granularity, like words, subwords, or characters. But most neural machine translation systems require the sentence to be represented as a sequence at a single level of granularity. It can be difficult to determine which granularity is better for a particular translation task. In this paper, we improve the model by incorporating multiple levels of granularity. Specifically, we propose (1) an encoder with character attention which augments the (sub)word-level representation with character-level information; (2) a decoder with multiple attentions that enable the representations from different levels of granularity to control the translation cooperatively. Experiments on three translation tasks demonstrate that our proposed models outperform the standard word-based model, the subword-based model, and a strong character-based model.
%R 10.18653/v1/N18-1116
%U https://aclanthology.org/N18-1116/
%U https://doi.org/10.18653/v1/N18-1116
%P 1284-1293
Markdown (Informal)
[Combining Character and Word Information in Neural Machine Translation Using a Multi-Level Attention](https://aclanthology.org/N18-1116/) (Chen et al., NAACL 2018)
ACL