@inproceedings{lu-etal-2016-multi-prototype,
title = "Multi-prototype {C}hinese Character Embedding",
author = "Lu, Yanan and
Zhang, Yue and
Ji, Donghong",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1138",
pages = "855--859",
abstract = "Chinese sentences are written as sequences of characters, which are elementary units of syntax and semantics. Characters are highly polysemous in forming words. We present a position-sensitive skip-gram model to learn multi-prototype Chinese character embeddings, and explore the usefulness of such character embeddings to Chinese NLP tasks. Evaluation on character similarity shows that multi-prototype embeddings are significantly better than a single-prototype baseline. In addition, used as features in the Chinese NER task, the embeddings result in a 1.74{\%} F-score improvement over a state-of-the-art baseline.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lu-etal-2016-multi-prototype">
<titleInfo>
<title>Multi-prototype Chinese Character Embedding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yanan</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Donghong</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Chinese sentences are written as sequences of characters, which are elementary units of syntax and semantics. Characters are highly polysemous in forming words. We present a position-sensitive skip-gram model to learn multi-prototype Chinese character embeddings, and explore the usefulness of such character embeddings to Chinese NLP tasks. Evaluation on character similarity shows that multi-prototype embeddings are significantly better than a single-prototype baseline. In addition, used as features in the Chinese NER task, the embeddings result in a 1.74% F-score improvement over a state-of-the-art baseline.</abstract>
<identifier type="citekey">lu-etal-2016-multi-prototype</identifier>
<location>
<url>https://aclanthology.org/L16-1138</url>
</location>
<part>
<date>2016-may</date>
<extent unit="page">
<start>855</start>
<end>859</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-prototype Chinese Character Embedding
%A Lu, Yanan
%A Zhang, Yue
%A Ji, Donghong
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 may
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F lu-etal-2016-multi-prototype
%X Chinese sentences are written as sequences of characters, which are elementary units of syntax and semantics. Characters are highly polysemous in forming words. We present a position-sensitive skip-gram model to learn multi-prototype Chinese character embeddings, and explore the usefulness of such character embeddings to Chinese NLP tasks. Evaluation on character similarity shows that multi-prototype embeddings are significantly better than a single-prototype baseline. In addition, used as features in the Chinese NER task, the embeddings result in a 1.74% F-score improvement over a state-of-the-art baseline.
%U https://aclanthology.org/L16-1138
%P 855-859
Markdown (Informal)
[Multi-prototype Chinese Character Embedding](https://aclanthology.org/L16-1138) (Lu et al., LREC 2016)
ACL
- Yanan Lu, Yue Zhang, and Donghong Ji. 2016. Multi-prototype Chinese Character Embedding. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 855–859, Portorož, Slovenia. European Language Resources Association (ELRA).