@inproceedings{sato-etal-2020-vocabulary,
title = "Vocabulary Adaptation for Domain Adaptation in Neural Machine Translation",
author = "Sato, Shoetsu and
Sakuma, Jin and
Yoshinaga, Naoki and
Toyoda, Masashi and
Kitsuregawa, Masaru",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.381",
doi = "10.18653/v1/2020.findings-emnlp.381",
pages = "4269--4279",
abstract = "Neural network methods exhibit strong performance only in a few resource-rich domains. Practitioners therefore employ domain adaptation from resource-rich domains that are, in most cases, distant from the target domain. Domain adaptation between distant domains (e.g., movie subtitles and research papers), however, cannot be performed effectively due to mismatches in vocabulary; it will encounter many domain-specific words (e.g., {``}angstrom{''}) and words whose meanings shift across domains (e.g., {``}conductor{''}). In this study, aiming to solve these vocabulary mismatches in domain adaptation for neural machine translation (NMT), we propose vocabulary adaptation, a simple method for effective fine-tuning that adapts embedding layers in a given pretrained NMT model to the target domain. Prior to fine-tuning, our method replaces the embedding layers of the NMT model by projecting general word embeddings induced from monolingual data in a target domain onto a source-domain embedding space. Experimental results indicate that our method improves the performance of conventional fine-tuning by 3.86 and 3.28 BLEU points in En-Ja and De-En translation, respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sato-etal-2020-vocabulary">
<titleInfo>
<title>Vocabulary Adaptation for Domain Adaptation in Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shoetsu</namePart>
<namePart type="family">Sato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jin</namePart>
<namePart type="family">Sakuma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoki</namePart>
<namePart type="family">Yoshinaga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masashi</namePart>
<namePart type="family">Toyoda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masaru</namePart>
<namePart type="family">Kitsuregawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Neural network methods exhibit strong performance only in a few resource-rich domains. Practitioners therefore employ domain adaptation from resource-rich domains that are, in most cases, distant from the target domain. Domain adaptation between distant domains (e.g., movie subtitles and research papers), however, cannot be performed effectively due to mismatches in vocabulary; it will encounter many domain-specific words (e.g., “angstrom”) and words whose meanings shift across domains (e.g., “conductor”). In this study, aiming to solve these vocabulary mismatches in domain adaptation for neural machine translation (NMT), we propose vocabulary adaptation, a simple method for effective fine-tuning that adapts embedding layers in a given pretrained NMT model to the target domain. Prior to fine-tuning, our method replaces the embedding layers of the NMT model by projecting general word embeddings induced from monolingual data in a target domain onto a source-domain embedding space. Experimental results indicate that our method improves the performance of conventional fine-tuning by 3.86 and 3.28 BLEU points in En-Ja and De-En translation, respectively.</abstract>
<identifier type="citekey">sato-etal-2020-vocabulary</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.381</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.381</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>4269</start>
<end>4279</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Vocabulary Adaptation for Domain Adaptation in Neural Machine Translation
%A Sato, Shoetsu
%A Sakuma, Jin
%A Yoshinaga, Naoki
%A Toyoda, Masashi
%A Kitsuregawa, Masaru
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F sato-etal-2020-vocabulary
%X Neural network methods exhibit strong performance only in a few resource-rich domains. Practitioners therefore employ domain adaptation from resource-rich domains that are, in most cases, distant from the target domain. Domain adaptation between distant domains (e.g., movie subtitles and research papers), however, cannot be performed effectively due to mismatches in vocabulary; it will encounter many domain-specific words (e.g., “angstrom”) and words whose meanings shift across domains (e.g., “conductor”). In this study, aiming to solve these vocabulary mismatches in domain adaptation for neural machine translation (NMT), we propose vocabulary adaptation, a simple method for effective fine-tuning that adapts embedding layers in a given pretrained NMT model to the target domain. Prior to fine-tuning, our method replaces the embedding layers of the NMT model by projecting general word embeddings induced from monolingual data in a target domain onto a source-domain embedding space. Experimental results indicate that our method improves the performance of conventional fine-tuning by 3.86 and 3.28 BLEU points in En-Ja and De-En translation, respectively.
%R 10.18653/v1/2020.findings-emnlp.381
%U https://aclanthology.org/2020.findings-emnlp.381
%U https://doi.org/10.18653/v1/2020.findings-emnlp.381
%P 4269-4279
Markdown (Informal)
[Vocabulary Adaptation for Domain Adaptation in Neural Machine Translation](https://aclanthology.org/2020.findings-emnlp.381) (Sato et al., Findings 2020)
ACL