@inproceedings{huang-etal-2018-multi,
title = "Multi-lingual Common Semantic Space Construction via Cluster-consistent Word Embedding",
author = "Huang, Lifu and
Cho, Kyunghyun and
Zhang, Boliang and
Ji, Heng and
Knight, Kevin",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
month = oct # "-" # nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D18-1023",
doi = "10.18653/v1/D18-1023",
pages = "250--260",
abstract = "We construct a multilingual common semantic space based on distributional semantics, where words from multiple languages are projected into a shared space via which all available resources and knowledge can be shared across multiple languages. Beyond word alignment, we introduce multiple cluster-level alignments and enforce the word clusters to be consistently distributed across multiple languages. We exploit three signals for clustering: (1) neighbor words in the monolingual word embedding space; (2) character-level information; and (3) linguistic properties (e.g., apposition, locative suffix) derived from linguistic structure knowledge bases available for thousands of languages. We introduce a new cluster-consistent correlational neural network to construct the common semantic space by aligning words as well as clusters. Intrinsic evaluation on monolingual and multilingual QVEC tasks shows our approach achieves significantly higher correlation with linguistic features which are extracted from manually crafted lexical resources than state-of-the-art multi-lingual embedding learning methods do. Using low-resource language name tagging as a case study for extrinsic evaluation, our approach achieves up to 14.6{\%} absolute F-score gain over the state of the art on cross-lingual direct transfer. Our approach is also shown to be robust even when the size of bilingual dictionary is small.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2018-multi">
<titleInfo>
<title>Multi-lingual Common Semantic Space Construction via Cluster-consistent Word Embedding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lifu</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyunghyun</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boliang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Knight</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-oct"-"nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We construct a multilingual common semantic space based on distributional semantics, where words from multiple languages are projected into a shared space via which all available resources and knowledge can be shared across multiple languages. Beyond word alignment, we introduce multiple cluster-level alignments and enforce the word clusters to be consistently distributed across multiple languages. We exploit three signals for clustering: (1) neighbor words in the monolingual word embedding space; (2) character-level information; and (3) linguistic properties (e.g., apposition, locative suffix) derived from linguistic structure knowledge bases available for thousands of languages. We introduce a new cluster-consistent correlational neural network to construct the common semantic space by aligning words as well as clusters. Intrinsic evaluation on monolingual and multilingual QVEC tasks shows our approach achieves significantly higher correlation with linguistic features which are extracted from manually crafted lexical resources than state-of-the-art multi-lingual embedding learning methods do. Using low-resource language name tagging as a case study for extrinsic evaluation, our approach achieves up to 14.6% absolute F-score gain over the state of the art on cross-lingual direct transfer. Our approach is also shown to be robust even when the size of bilingual dictionary is small.</abstract>
<identifier type="citekey">huang-etal-2018-multi</identifier>
<identifier type="doi">10.18653/v1/D18-1023</identifier>
<location>
<url>https://aclanthology.org/D18-1023</url>
</location>
<part>
<date>2018-oct"-"nov</date>
<extent unit="page">
<start>250</start>
<end>260</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-lingual Common Semantic Space Construction via Cluster-consistent Word Embedding
%A Huang, Lifu
%A Cho, Kyunghyun
%A Zhang, Boliang
%A Ji, Heng
%A Knight, Kevin
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct" "nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F huang-etal-2018-multi
%X We construct a multilingual common semantic space based on distributional semantics, where words from multiple languages are projected into a shared space via which all available resources and knowledge can be shared across multiple languages. Beyond word alignment, we introduce multiple cluster-level alignments and enforce the word clusters to be consistently distributed across multiple languages. We exploit three signals for clustering: (1) neighbor words in the monolingual word embedding space; (2) character-level information; and (3) linguistic properties (e.g., apposition, locative suffix) derived from linguistic structure knowledge bases available for thousands of languages. We introduce a new cluster-consistent correlational neural network to construct the common semantic space by aligning words as well as clusters. Intrinsic evaluation on monolingual and multilingual QVEC tasks shows our approach achieves significantly higher correlation with linguistic features which are extracted from manually crafted lexical resources than state-of-the-art multi-lingual embedding learning methods do. Using low-resource language name tagging as a case study for extrinsic evaluation, our approach achieves up to 14.6% absolute F-score gain over the state of the art on cross-lingual direct transfer. Our approach is also shown to be robust even when the size of bilingual dictionary is small.
%R 10.18653/v1/D18-1023
%U https://aclanthology.org/D18-1023
%U https://doi.org/10.18653/v1/D18-1023
%P 250-260
Markdown (Informal)
[Multi-lingual Common Semantic Space Construction via Cluster-consistent Word Embedding](https://aclanthology.org/D18-1023) (Huang et al., EMNLP 2018)
ACL