@inproceedings{hakimi-parizi-cook-2020-evaluating,
title = "Evaluating Sub-word Embeddings in Cross-lingual Models",
author = "Hakimi Parizi, Ali and
Cook, Paul",
booktitle = "Proceedings of the 12th Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.330",
pages = "2712--2719",
abstract = "Cross-lingual word embeddings create a shared space for embeddings in two languages, and enable knowledge to be transferred between languages for tasks such as bilingual lexicon induction. One problem, however, is out-of-vocabulary (OOV) words, for which no embeddings are available. This is particularly problematic for low-resource and morphologically-rich languages, which often have relatively high OOV rates. Approaches to learning sub-word embeddings have been proposed to address the problem of OOV words, but most prior work has not considered sub-word embeddings in cross-lingual models. In this paper, we consider whether sub-word embeddings can be leveraged to form cross-lingual embeddings for OOV words. Specifically, we consider a novel bilingual lexicon induction task focused on OOV words, for language pairs covering several language families. Our results indicate that cross-lingual representations for OOV words can indeed be formed from sub-word embeddings, including in the case of a truly low-resource morphologically-rich language.",
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="hakimi-parizi-cook-2020-evaluating">
<titleInfo>
<title>Evaluating Sub-word Embeddings in Cross-lingual Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Hakimi Parizi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Cook</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-may</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 12th Language Resources and Evaluation Conference</title>
</titleInfo>
<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>Cross-lingual word embeddings create a shared space for embeddings in two languages, and enable knowledge to be transferred between languages for tasks such as bilingual lexicon induction. One problem, however, is out-of-vocabulary (OOV) words, for which no embeddings are available. This is particularly problematic for low-resource and morphologically-rich languages, which often have relatively high OOV rates. Approaches to learning sub-word embeddings have been proposed to address the problem of OOV words, but most prior work has not considered sub-word embeddings in cross-lingual models. In this paper, we consider whether sub-word embeddings can be leveraged to form cross-lingual embeddings for OOV words. Specifically, we consider a novel bilingual lexicon induction task focused on OOV words, for language pairs covering several language families. Our results indicate that cross-lingual representations for OOV words can indeed be formed from sub-word embeddings, including in the case of a truly low-resource morphologically-rich language.</abstract>
<identifier type="citekey">hakimi-parizi-cook-2020-evaluating</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.330</url>
</location>
<part>
<date>2020-may</date>
<extent unit="page">
<start>2712</start>
<end>2719</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Sub-word Embeddings in Cross-lingual Models
%A Hakimi Parizi, Ali
%A Cook, Paul
%S Proceedings of the 12th 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 hakimi-parizi-cook-2020-evaluating
%X Cross-lingual word embeddings create a shared space for embeddings in two languages, and enable knowledge to be transferred between languages for tasks such as bilingual lexicon induction. One problem, however, is out-of-vocabulary (OOV) words, for which no embeddings are available. This is particularly problematic for low-resource and morphologically-rich languages, which often have relatively high OOV rates. Approaches to learning sub-word embeddings have been proposed to address the problem of OOV words, but most prior work has not considered sub-word embeddings in cross-lingual models. In this paper, we consider whether sub-word embeddings can be leveraged to form cross-lingual embeddings for OOV words. Specifically, we consider a novel bilingual lexicon induction task focused on OOV words, for language pairs covering several language families. Our results indicate that cross-lingual representations for OOV words can indeed be formed from sub-word embeddings, including in the case of a truly low-resource morphologically-rich language.
%U https://aclanthology.org/2020.lrec-1.330
%P 2712-2719
Markdown (Informal)
[Evaluating Sub-word Embeddings in Cross-lingual Models](https://aclanthology.org/2020.lrec-1.330) (Hakimi Parizi & Cook, LREC 2020)
ACL