@inproceedings{passban-etal-2018-improving,
title = "Improving Character-Based Decoding Using Target-Side Morphological Information for Neural Machine Translation",
author = "Passban, Peyman and
Liu, Qun and
Way, Andy",
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/N18-1006",
doi = "10.18653/v1/N18-1006",
pages = "58--68",
abstract = "Recently, neural machine translation (NMT) has emerged as a powerful alternative to conventional statistical approaches. However, its performance drops considerably in the presence of morphologically rich languages (MRLs). Neural engines usually fail to tackle the large vocabulary and high out-of-vocabulary (OOV) word rate of MRLs. Therefore, it is not suitable to exploit existing word-based models to translate this set of languages. In this paper, we propose an extension to the state-of-the-art model of Chung et al. (2016), which works at the character level and boosts the decoder with target-side morphological information. In our architecture, an additional morphology table is plugged into the model. Each time the decoder samples from a target vocabulary, the table sends auxiliary signals from the most relevant affixes in order to enrich the decoder{'}s current state and constrain it to provide better predictions. We evaluated our model to translate English into German, Russian, and Turkish as three MRLs and observed significant improvements.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="passban-etal-2018-improving">
<titleInfo>
<title>Improving Character-Based Decoding Using Target-Side Morphological Information for Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Peyman</namePart>
<namePart type="family">Passban</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qun</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andy</namePart>
<namePart type="family">Way</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>Recently, neural machine translation (NMT) has emerged as a powerful alternative to conventional statistical approaches. However, its performance drops considerably in the presence of morphologically rich languages (MRLs). Neural engines usually fail to tackle the large vocabulary and high out-of-vocabulary (OOV) word rate of MRLs. Therefore, it is not suitable to exploit existing word-based models to translate this set of languages. In this paper, we propose an extension to the state-of-the-art model of Chung et al. (2016), which works at the character level and boosts the decoder with target-side morphological information. In our architecture, an additional morphology table is plugged into the model. Each time the decoder samples from a target vocabulary, the table sends auxiliary signals from the most relevant affixes in order to enrich the decoder’s current state and constrain it to provide better predictions. We evaluated our model to translate English into German, Russian, and Turkish as three MRLs and observed significant improvements.</abstract>
<identifier type="citekey">passban-etal-2018-improving</identifier>
<identifier type="doi">10.18653/v1/N18-1006</identifier>
<location>
<url>https://aclanthology.org/N18-1006</url>
</location>
<part>
<date>2018-06</date>
<extent unit="page">
<start>58</start>
<end>68</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Character-Based Decoding Using Target-Side Morphological Information for Neural Machine Translation
%A Passban, Peyman
%A Liu, Qun
%A Way, Andy
%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 passban-etal-2018-improving
%X Recently, neural machine translation (NMT) has emerged as a powerful alternative to conventional statistical approaches. However, its performance drops considerably in the presence of morphologically rich languages (MRLs). Neural engines usually fail to tackle the large vocabulary and high out-of-vocabulary (OOV) word rate of MRLs. Therefore, it is not suitable to exploit existing word-based models to translate this set of languages. In this paper, we propose an extension to the state-of-the-art model of Chung et al. (2016), which works at the character level and boosts the decoder with target-side morphological information. In our architecture, an additional morphology table is plugged into the model. Each time the decoder samples from a target vocabulary, the table sends auxiliary signals from the most relevant affixes in order to enrich the decoder’s current state and constrain it to provide better predictions. We evaluated our model to translate English into German, Russian, and Turkish as three MRLs and observed significant improvements.
%R 10.18653/v1/N18-1006
%U https://aclanthology.org/N18-1006
%U https://doi.org/10.18653/v1/N18-1006
%P 58-68
Markdown (Informal)
[Improving Character-Based Decoding Using Target-Side Morphological Information for Neural Machine Translation](https://aclanthology.org/N18-1006) (Passban et al., NAACL 2018)
ACL