@inproceedings{xu-etal-2020-unihanlm,
title = "{U}nihan{LM}: Coarse-to-Fine {C}hinese-{J}apanese Language Model Pretraining with the Unihan Database",
author = "Xu, Canwen and
Ge, Tao and
Li, Chenliang and
Wei, Furu",
editor = "Wong, Kam-Fai and
Knight, Kevin and
Wu, Hua",
booktitle = "Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing",
month = dec,
year = "2020",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.aacl-main.24",
pages = "201--211",
abstract = "Chinese and Japanese share many characters with similar surface morphology. To better utilize the shared knowledge across the languages, we propose UnihanLM, a self-supervised Chinese-Japanese pretrained masked language model (MLM) with a novel two-stage coarse-to-fine training approach. We exploit Unihan, a ready-made database constructed by linguistic experts to first merge morphologically similar characters into clusters. The resulting clusters are used to replace the original characters in sentences for the coarse-grained pretraining of the MLM. Then, we restore the clusters back to the original characters in sentences for the fine-grained pretraining to learn the representation of the specific characters. We conduct extensive experiments on a variety of Chinese and Japanese NLP benchmarks, showing that our proposed UnihanLM is effective on both mono- and cross-lingual Chinese and Japanese tasks, shedding light on a new path to exploit the homology of languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2020-unihanlm">
<titleInfo>
<title>UnihanLM: Coarse-to-Fine Chinese-Japanese Language Model Pretraining with the Unihan Database</title>
</titleInfo>
<name type="personal">
<namePart type="given">Canwen</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Ge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenliang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Furu</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kam-Fai</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Knight</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Chinese and Japanese share many characters with similar surface morphology. To better utilize the shared knowledge across the languages, we propose UnihanLM, a self-supervised Chinese-Japanese pretrained masked language model (MLM) with a novel two-stage coarse-to-fine training approach. We exploit Unihan, a ready-made database constructed by linguistic experts to first merge morphologically similar characters into clusters. The resulting clusters are used to replace the original characters in sentences for the coarse-grained pretraining of the MLM. Then, we restore the clusters back to the original characters in sentences for the fine-grained pretraining to learn the representation of the specific characters. We conduct extensive experiments on a variety of Chinese and Japanese NLP benchmarks, showing that our proposed UnihanLM is effective on both mono- and cross-lingual Chinese and Japanese tasks, shedding light on a new path to exploit the homology of languages.</abstract>
<identifier type="citekey">xu-etal-2020-unihanlm</identifier>
<location>
<url>https://aclanthology.org/2020.aacl-main.24</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>201</start>
<end>211</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UnihanLM: Coarse-to-Fine Chinese-Japanese Language Model Pretraining with the Unihan Database
%A Xu, Canwen
%A Ge, Tao
%A Li, Chenliang
%A Wei, Furu
%Y Wong, Kam-Fai
%Y Knight, Kevin
%Y Wu, Hua
%S Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing
%D 2020
%8 December
%I Association for Computational Linguistics
%C Suzhou, China
%F xu-etal-2020-unihanlm
%X Chinese and Japanese share many characters with similar surface morphology. To better utilize the shared knowledge across the languages, we propose UnihanLM, a self-supervised Chinese-Japanese pretrained masked language model (MLM) with a novel two-stage coarse-to-fine training approach. We exploit Unihan, a ready-made database constructed by linguistic experts to first merge morphologically similar characters into clusters. The resulting clusters are used to replace the original characters in sentences for the coarse-grained pretraining of the MLM. Then, we restore the clusters back to the original characters in sentences for the fine-grained pretraining to learn the representation of the specific characters. We conduct extensive experiments on a variety of Chinese and Japanese NLP benchmarks, showing that our proposed UnihanLM is effective on both mono- and cross-lingual Chinese and Japanese tasks, shedding light on a new path to exploit the homology of languages.
%U https://aclanthology.org/2020.aacl-main.24
%P 201-211
Markdown (Informal)
[UnihanLM: Coarse-to-Fine Chinese-Japanese Language Model Pretraining with the Unihan Database](https://aclanthology.org/2020.aacl-main.24) (Xu et al., AACL 2020)
ACL