@inproceedings{mulcaire-etal-2019-polyglot,
title = "Polyglot Contextual Representations Improve Crosslingual Transfer",
author = "Mulcaire, Phoebe and
Kasai, Jungo and
Smith, Noah A.",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1392",
doi = "10.18653/v1/N19-1392",
pages = "3912--3918",
abstract = "We introduce Rosita, a method to produce multilingual contextual word representations by training a single language model on text from multiple languages. Our method combines the advantages of contextual word representations with those of multilingual representation learning. We produce language models from dissimilar language pairs (English/Arabic and English/Chinese) and use them in dependency parsing, semantic role labeling, and named entity recognition, with comparisons to monolingual and non-contextual variants. Our results provide further evidence for the benefits of polyglot learning, in which representations are shared across multiple languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mulcaire-etal-2019-polyglot">
<titleInfo>
<title>Polyglot Contextual Representations Improve Crosslingual Transfer</title>
</titleInfo>
<name type="personal">
<namePart type="given">Phoebe</namePart>
<namePart type="family">Mulcaire</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jungo</namePart>
<namePart type="family">Kasai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noah</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Smith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-jun</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce Rosita, a method to produce multilingual contextual word representations by training a single language model on text from multiple languages. Our method combines the advantages of contextual word representations with those of multilingual representation learning. We produce language models from dissimilar language pairs (English/Arabic and English/Chinese) and use them in dependency parsing, semantic role labeling, and named entity recognition, with comparisons to monolingual and non-contextual variants. Our results provide further evidence for the benefits of polyglot learning, in which representations are shared across multiple languages.</abstract>
<identifier type="citekey">mulcaire-etal-2019-polyglot</identifier>
<identifier type="doi">10.18653/v1/N19-1392</identifier>
<location>
<url>https://aclanthology.org/N19-1392</url>
</location>
<part>
<date>2019-jun</date>
<extent unit="page">
<start>3912</start>
<end>3918</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Polyglot Contextual Representations Improve Crosslingual Transfer
%A Mulcaire, Phoebe
%A Kasai, Jungo
%A Smith, Noah A.
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 jun
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F mulcaire-etal-2019-polyglot
%X We introduce Rosita, a method to produce multilingual contextual word representations by training a single language model on text from multiple languages. Our method combines the advantages of contextual word representations with those of multilingual representation learning. We produce language models from dissimilar language pairs (English/Arabic and English/Chinese) and use them in dependency parsing, semantic role labeling, and named entity recognition, with comparisons to monolingual and non-contextual variants. Our results provide further evidence for the benefits of polyglot learning, in which representations are shared across multiple languages.
%R 10.18653/v1/N19-1392
%U https://aclanthology.org/N19-1392
%U https://doi.org/10.18653/v1/N19-1392
%P 3912-3918
Markdown (Informal)
[Polyglot Contextual Representations Improve Crosslingual Transfer](https://aclanthology.org/N19-1392) (Mulcaire et al., NAACL 2019)
ACL
- Phoebe Mulcaire, Jungo Kasai, and Noah A. Smith. 2019. Polyglot Contextual Representations Improve Crosslingual Transfer. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 3912–3918, Minneapolis, Minnesota. Association for Computational Linguistics.