@inproceedings{bhattacharya-etal-2016-query,
title = "Query Translation for Cross-Language Information Retrieval using Multilingual Word Clusters",
author = "Bhattacharya, Paheli and
Goyal, Pawan and
Sarkar, Sudeshna",
editor = "Wu, Dekai and
Bhattacharyya, Pushpak",
booktitle = "Proceedings of the 6th Workshop on South and Southeast {A}sian Natural Language Processing ({WSSANLP}2016)",
month = dec,
year = "2016",
address = "Osaka, Japan",
publisher = "The COLING 2016 Organizing Committee",
url = "https://aclanthology.org/W16-3716",
pages = "152--162",
abstract = "In Cross-Language Information Retrieval, finding the appropriate translation of the source language query has always been a difficult problem to solve. We propose a technique towards solving this problem with the help of multilingual word clusters obtained from multilingual word embeddings. We use word embeddings of the languages projected to a common vector space on which a community-detection algorithm is applied to find clusters such that words that represent the same concept from different languages fall in the same group. We utilize these multilingual word clusters to perform query translation for Cross-Language Information Retrieval for three languages - English, Hindi and Bengali. We have experimented with the FIRE 2012 and Wikipedia datasets and have shown improvements over several standard methods like dictionary-based method, a transliteration-based model and Google Translate.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhattacharya-etal-2016-query">
<titleInfo>
<title>Query Translation for Cross-Language Information Retrieval using Multilingual Word Clusters</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paheli</namePart>
<namePart type="family">Bhattacharya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pawan</namePart>
<namePart type="family">Goyal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sudeshna</namePart>
<namePart type="family">Sarkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Workshop on South and Southeast Asian Natural Language Processing (WSSANLP2016)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dekai</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The COLING 2016 Organizing Committee</publisher>
<place>
<placeTerm type="text">Osaka, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In Cross-Language Information Retrieval, finding the appropriate translation of the source language query has always been a difficult problem to solve. We propose a technique towards solving this problem with the help of multilingual word clusters obtained from multilingual word embeddings. We use word embeddings of the languages projected to a common vector space on which a community-detection algorithm is applied to find clusters such that words that represent the same concept from different languages fall in the same group. We utilize these multilingual word clusters to perform query translation for Cross-Language Information Retrieval for three languages - English, Hindi and Bengali. We have experimented with the FIRE 2012 and Wikipedia datasets and have shown improvements over several standard methods like dictionary-based method, a transliteration-based model and Google Translate.</abstract>
<identifier type="citekey">bhattacharya-etal-2016-query</identifier>
<location>
<url>https://aclanthology.org/W16-3716</url>
</location>
<part>
<date>2016-12</date>
<extent unit="page">
<start>152</start>
<end>162</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Query Translation for Cross-Language Information Retrieval using Multilingual Word Clusters
%A Bhattacharya, Paheli
%A Goyal, Pawan
%A Sarkar, Sudeshna
%Y Wu, Dekai
%Y Bhattacharyya, Pushpak
%S Proceedings of the 6th Workshop on South and Southeast Asian Natural Language Processing (WSSANLP2016)
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F bhattacharya-etal-2016-query
%X In Cross-Language Information Retrieval, finding the appropriate translation of the source language query has always been a difficult problem to solve. We propose a technique towards solving this problem with the help of multilingual word clusters obtained from multilingual word embeddings. We use word embeddings of the languages projected to a common vector space on which a community-detection algorithm is applied to find clusters such that words that represent the same concept from different languages fall in the same group. We utilize these multilingual word clusters to perform query translation for Cross-Language Information Retrieval for three languages - English, Hindi and Bengali. We have experimented with the FIRE 2012 and Wikipedia datasets and have shown improvements over several standard methods like dictionary-based method, a transliteration-based model and Google Translate.
%U https://aclanthology.org/W16-3716
%P 152-162
Markdown (Informal)
[Query Translation for Cross-Language Information Retrieval using Multilingual Word Clusters](https://aclanthology.org/W16-3716) (Bhattacharya et al., WSSANLP 2016)
ACL