@inproceedings{li-etal-2021-char,
title = "When is Char Better Than Subword: A Systematic Study of Segmentation Algorithms for Neural Machine Translation",
author = "Li, Jiahuan and
Shen, Yutong and
Huang, Shujian and
Dai, Xinyu and
Chen, Jiajun",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-short.69",
doi = "10.18653/v1/2021.acl-short.69",
pages = "543--549",
abstract = "Subword segmentation algorithms have been a \textit{de facto} choice when building neural machine translation systems. However, most of them need to learn a segmentation model based on some heuristics, which may produce sub-optimal segmentation. This can be problematic in some scenarios when the target language has rich morphological changes or there is not enough data for learning compact composition rules. Translating at fully character level has the potential to alleviate the issue, but empirical performances of character-based models has not been fully explored. In this paper, we present an in-depth comparison between character-based and subword-based NMT systems under three settings: translating to typologically diverse languages, training with low resource, and adapting to unseen domains. Experiment results show strong competitiveness of character-based models. Further analyses show that compared to subword-based models, character-based models are better at handling morphological phenomena, generating rare and unknown words, and more suitable for transferring to unseen domains.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2021-char">
<titleInfo>
<title>When is Char Better Than Subword: A Systematic Study of Segmentation Algorithms for Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiahuan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yutong</namePart>
<namePart type="family">Shen</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">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>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</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>Subword segmentation algorithms have been a de facto choice when building neural machine translation systems. However, most of them need to learn a segmentation model based on some heuristics, which may produce sub-optimal segmentation. This can be problematic in some scenarios when the target language has rich morphological changes or there is not enough data for learning compact composition rules. Translating at fully character level has the potential to alleviate the issue, but empirical performances of character-based models has not been fully explored. In this paper, we present an in-depth comparison between character-based and subword-based NMT systems under three settings: translating to typologically diverse languages, training with low resource, and adapting to unseen domains. Experiment results show strong competitiveness of character-based models. Further analyses show that compared to subword-based models, character-based models are better at handling morphological phenomena, generating rare and unknown words, and more suitable for transferring to unseen domains.</abstract>
<identifier type="citekey">li-etal-2021-char</identifier>
<identifier type="doi">10.18653/v1/2021.acl-short.69</identifier>
<location>
<url>https://aclanthology.org/2021.acl-short.69</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>543</start>
<end>549</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T When is Char Better Than Subword: A Systematic Study of Segmentation Algorithms for Neural Machine Translation
%A Li, Jiahuan
%A Shen, Yutong
%A Huang, Shujian
%A Dai, Xinyu
%A Chen, Jiajun
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F li-etal-2021-char
%X Subword segmentation algorithms have been a de facto choice when building neural machine translation systems. However, most of them need to learn a segmentation model based on some heuristics, which may produce sub-optimal segmentation. This can be problematic in some scenarios when the target language has rich morphological changes or there is not enough data for learning compact composition rules. Translating at fully character level has the potential to alleviate the issue, but empirical performances of character-based models has not been fully explored. In this paper, we present an in-depth comparison between character-based and subword-based NMT systems under three settings: translating to typologically diverse languages, training with low resource, and adapting to unseen domains. Experiment results show strong competitiveness of character-based models. Further analyses show that compared to subword-based models, character-based models are better at handling morphological phenomena, generating rare and unknown words, and more suitable for transferring to unseen domains.
%R 10.18653/v1/2021.acl-short.69
%U https://aclanthology.org/2021.acl-short.69
%U https://doi.org/10.18653/v1/2021.acl-short.69
%P 543-549
Markdown (Informal)
[When is Char Better Than Subword: A Systematic Study of Segmentation Algorithms for Neural Machine Translation](https://aclanthology.org/2021.acl-short.69) (Li et al., ACL-IJCNLP 2021)
ACL