@inproceedings{kim-etal-2020-representation,
title = "Representation Learning for Unseen Words by Bridging Subwords to Semantic Networks",
author = "Kim, Yeachan and
Kim, Kang-Min and
Lee, SangKeun",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.587",
pages = "4774--4780",
abstract = "Pre-trained word embeddings are widely used in various fields. However, the coverage of pre-trained word embeddings only includes words that appeared in corpora where pre-trained embeddings are learned. It means that the words which do not appear in training corpus are ignored in tasks, and it could lead to the limited performance of neural models. In this paper, we propose a simple yet effective method to represent out-of-vocabulary (OOV) words. Unlike prior works that solely utilize subword information or knowledge, our method makes use of both information to represent OOV words. To this end, we propose two stages of representation learning. In the first stage, we learn subword embeddings from the pre-trained word embeddings by using an additive composition function of subwords. In the second stage, we map the learned subwords into semantic networks (e.g., WordNet). We then re-train the subword embeddings by using lexical entries on semantic lexicons that could include newly observed subwords. This two-stage learning makes the coverage of words broaden to a great extent. The experimental results clearly show that our method provides consistent performance improvements over strong baselines that use subwords or lexical resources separately.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2020-representation">
<titleInfo>
<title>Representation Learning for Unseen Words by Bridging Subwords to Semantic Networks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yeachan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kang-Min</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">SangKeun</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Pre-trained word embeddings are widely used in various fields. However, the coverage of pre-trained word embeddings only includes words that appeared in corpora where pre-trained embeddings are learned. It means that the words which do not appear in training corpus are ignored in tasks, and it could lead to the limited performance of neural models. In this paper, we propose a simple yet effective method to represent out-of-vocabulary (OOV) words. Unlike prior works that solely utilize subword information or knowledge, our method makes use of both information to represent OOV words. To this end, we propose two stages of representation learning. In the first stage, we learn subword embeddings from the pre-trained word embeddings by using an additive composition function of subwords. In the second stage, we map the learned subwords into semantic networks (e.g., WordNet). We then re-train the subword embeddings by using lexical entries on semantic lexicons that could include newly observed subwords. This two-stage learning makes the coverage of words broaden to a great extent. The experimental results clearly show that our method provides consistent performance improvements over strong baselines that use subwords or lexical resources separately.</abstract>
<identifier type="citekey">kim-etal-2020-representation</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.587</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>4774</start>
<end>4780</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Representation Learning for Unseen Words by Bridging Subwords to Semantic Networks
%A Kim, Yeachan
%A Kim, Kang-Min
%A Lee, SangKeun
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F kim-etal-2020-representation
%X Pre-trained word embeddings are widely used in various fields. However, the coverage of pre-trained word embeddings only includes words that appeared in corpora where pre-trained embeddings are learned. It means that the words which do not appear in training corpus are ignored in tasks, and it could lead to the limited performance of neural models. In this paper, we propose a simple yet effective method to represent out-of-vocabulary (OOV) words. Unlike prior works that solely utilize subword information or knowledge, our method makes use of both information to represent OOV words. To this end, we propose two stages of representation learning. In the first stage, we learn subword embeddings from the pre-trained word embeddings by using an additive composition function of subwords. In the second stage, we map the learned subwords into semantic networks (e.g., WordNet). We then re-train the subword embeddings by using lexical entries on semantic lexicons that could include newly observed subwords. This two-stage learning makes the coverage of words broaden to a great extent. The experimental results clearly show that our method provides consistent performance improvements over strong baselines that use subwords or lexical resources separately.
%U https://aclanthology.org/2020.lrec-1.587
%P 4774-4780
Markdown (Informal)
[Representation Learning for Unseen Words by Bridging Subwords to Semantic Networks](https://aclanthology.org/2020.lrec-1.587) (Kim et al., LREC 2020)
ACL