@inproceedings{moshtaghi-2019-supervised,
title = "Supervised and Nonlinear Alignment of Two Embedding Spaces for Dictionary Induction in Low Resourced Languages",
author = "Moshtaghi, Masud",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1076",
doi = "10.18653/v1/D19-1076",
pages = "823--832",
abstract = "Enabling cross-lingual NLP tasks by leveraging multilingual word embedding has recently attracted much attention. An important motivation is to support lower resourced languages, however, most efforts focus on demonstrating the effectiveness of the techniques using embeddings derived from similar languages to English with large parallel content. In this study, we first describe the general requirements for the success of these techniques and then present a noise tolerant piecewise linear technique to learn a non-linear mapping between two monolingual word embedding vector spaces. We evaluate our approach on inferring bilingual dictionaries. We show that our technique outperforms the state-of-the-art in lower resourced settings with an average of 3.7{\%} improvement of precision @10 across 14 mostly low resourced languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="moshtaghi-2019-supervised">
<titleInfo>
<title>Supervised and Nonlinear Alignment of Two Embedding Spaces for Dictionary Induction in Low Resourced Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Masud</namePart>
<namePart type="family">Moshtaghi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Enabling cross-lingual NLP tasks by leveraging multilingual word embedding has recently attracted much attention. An important motivation is to support lower resourced languages, however, most efforts focus on demonstrating the effectiveness of the techniques using embeddings derived from similar languages to English with large parallel content. In this study, we first describe the general requirements for the success of these techniques and then present a noise tolerant piecewise linear technique to learn a non-linear mapping between two monolingual word embedding vector spaces. We evaluate our approach on inferring bilingual dictionaries. We show that our technique outperforms the state-of-the-art in lower resourced settings with an average of 3.7% improvement of precision @10 across 14 mostly low resourced languages.</abstract>
<identifier type="citekey">moshtaghi-2019-supervised</identifier>
<identifier type="doi">10.18653/v1/D19-1076</identifier>
<location>
<url>https://aclanthology.org/D19-1076</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>823</start>
<end>832</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Supervised and Nonlinear Alignment of Two Embedding Spaces for Dictionary Induction in Low Resourced Languages
%A Moshtaghi, Masud
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F moshtaghi-2019-supervised
%X Enabling cross-lingual NLP tasks by leveraging multilingual word embedding has recently attracted much attention. An important motivation is to support lower resourced languages, however, most efforts focus on demonstrating the effectiveness of the techniques using embeddings derived from similar languages to English with large parallel content. In this study, we first describe the general requirements for the success of these techniques and then present a noise tolerant piecewise linear technique to learn a non-linear mapping between two monolingual word embedding vector spaces. We evaluate our approach on inferring bilingual dictionaries. We show that our technique outperforms the state-of-the-art in lower resourced settings with an average of 3.7% improvement of precision @10 across 14 mostly low resourced languages.
%R 10.18653/v1/D19-1076
%U https://aclanthology.org/D19-1076
%U https://doi.org/10.18653/v1/D19-1076
%P 823-832
Markdown (Informal)
[Supervised and Nonlinear Alignment of Two Embedding Spaces for Dictionary Induction in Low Resourced Languages](https://aclanthology.org/D19-1076) (Moshtaghi, EMNLP-IJCNLP 2019)
ACL