@inproceedings{lu-etal-2016-multi-prototype,
title = "Multi-prototype {C}hinese Character Embedding",
author = "Lu, Yanan and
Zhang, Yue and
Ji, Donghong",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
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>2016-05</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>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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>2016-05</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
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%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).