@inproceedings{chidambaram-etal-2019-learning,
title = "Learning Cross-Lingual Sentence Representations via a Multi-task Dual-Encoder Model",
author = "Chidambaram, Muthu and
Yang, Yinfei and
Cer, Daniel and
Yuan, Steve and
Sung, Yunhsuan and
Strope, Brian and
Kurzweil, Ray",
editor = "Augenstein, Isabelle and
Gella, Spandana and
Ruder, Sebastian and
Kann, Katharina and
Can, Burcu and
Welbl, Johannes and
Conneau, Alexis and
Ren, Xiang and
Rei, Marek",
booktitle = "Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-4330",
doi = "10.18653/v1/W19-4330",
pages = "250--259",
abstract = "The scarcity of labeled training data across many languages is a significant roadblock for multilingual neural language processing. We approach the lack of in-language training data using sentence embeddings that map text written in different languages, but with similar meanings, to nearby embedding space representations. The representations are produced using a dual-encoder based model trained to maximize the representational similarity between sentence pairs drawn from parallel data. The representations are enhanced using multitask training and unsupervised monolingual corpora. The effectiveness of our multilingual sentence embeddings are assessed on a comprehensive collection of monolingual, cross-lingual, and zero-shot/few-shot learning tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chidambaram-etal-2019-learning">
<titleInfo>
<title>Learning Cross-Lingual Sentence Representations via a Multi-task Dual-Encoder Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muthu</namePart>
<namePart type="family">Chidambaram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yinfei</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Cer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steve</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunhsuan</namePart>
<namePart type="family">Sung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="family">Strope</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ray</namePart>
<namePart type="family">Kurzweil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Spandana</namePart>
<namePart type="family">Gella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Ruder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katharina</namePart>
<namePart type="family">Kann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Burcu</namePart>
<namePart type="family">Can</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johannes</namePart>
<namePart type="family">Welbl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Conneau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marek</namePart>
<namePart type="family">Rei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The scarcity of labeled training data across many languages is a significant roadblock for multilingual neural language processing. We approach the lack of in-language training data using sentence embeddings that map text written in different languages, but with similar meanings, to nearby embedding space representations. The representations are produced using a dual-encoder based model trained to maximize the representational similarity between sentence pairs drawn from parallel data. The representations are enhanced using multitask training and unsupervised monolingual corpora. The effectiveness of our multilingual sentence embeddings are assessed on a comprehensive collection of monolingual, cross-lingual, and zero-shot/few-shot learning tasks.</abstract>
<identifier type="citekey">chidambaram-etal-2019-learning</identifier>
<identifier type="doi">10.18653/v1/W19-4330</identifier>
<location>
<url>https://aclanthology.org/W19-4330</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>250</start>
<end>259</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning Cross-Lingual Sentence Representations via a Multi-task Dual-Encoder Model
%A Chidambaram, Muthu
%A Yang, Yinfei
%A Cer, Daniel
%A Yuan, Steve
%A Sung, Yunhsuan
%A Strope, Brian
%A Kurzweil, Ray
%Y Augenstein, Isabelle
%Y Gella, Spandana
%Y Ruder, Sebastian
%Y Kann, Katharina
%Y Can, Burcu
%Y Welbl, Johannes
%Y Conneau, Alexis
%Y Ren, Xiang
%Y Rei, Marek
%S Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F chidambaram-etal-2019-learning
%X The scarcity of labeled training data across many languages is a significant roadblock for multilingual neural language processing. We approach the lack of in-language training data using sentence embeddings that map text written in different languages, but with similar meanings, to nearby embedding space representations. The representations are produced using a dual-encoder based model trained to maximize the representational similarity between sentence pairs drawn from parallel data. The representations are enhanced using multitask training and unsupervised monolingual corpora. The effectiveness of our multilingual sentence embeddings are assessed on a comprehensive collection of monolingual, cross-lingual, and zero-shot/few-shot learning tasks.
%R 10.18653/v1/W19-4330
%U https://aclanthology.org/W19-4330
%U https://doi.org/10.18653/v1/W19-4330
%P 250-259
Markdown (Informal)
[Learning Cross-Lingual Sentence Representations via a Multi-task Dual-Encoder Model](https://aclanthology.org/W19-4330) (Chidambaram et al., RepL4NLP 2019)
ACL