@inproceedings{kanojia-etal-2016-thatll,
title = "That{'}ll Do Fine!: A Coarse Lexical Resource for {E}nglish-{H}indi {MT}, Using Polylingual Topic Models",
author = "Kanojia, Diptesh and
Joshi, Aditya and
Bhattacharyya, Pushpak and
Carman, Mark James",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1349",
pages = "2199--2203",
abstract = "Parallel corpora are often injected with bilingual lexical resources for improved Indian language machine translation (MT). In absence of such lexical resources, multilingual topic models have been used to create coarse lexical resources in the past, using a Cartesian product approach. Our results show that for morphologically rich languages like Hindi, the Cartesian product approach is detrimental for MT. We then present a novel {`}sentential{'} approach to use this coarse lexical resource from a multilingual topic model. Our coarse lexical resource when injected with a parallel corpus outperforms a system trained using parallel corpus and a good quality lexical resource. As demonstrated by the quality of our coarse lexical resource and its benefit to MT, we believe that our sentential approach to create such a resource will help MT for resource-constrained languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kanojia-etal-2016-thatll">
<titleInfo>
<title>That’ll Do Fine!: A Coarse Lexical Resource for English-Hindi MT, Using Polylingual Topic Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Diptesh</namePart>
<namePart type="family">Kanojia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aditya</namePart>
<namePart type="family">Joshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="given">James</namePart>
<namePart type="family">Carman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Parallel corpora are often injected with bilingual lexical resources for improved Indian language machine translation (MT). In absence of such lexical resources, multilingual topic models have been used to create coarse lexical resources in the past, using a Cartesian product approach. Our results show that for morphologically rich languages like Hindi, the Cartesian product approach is detrimental for MT. We then present a novel ‘sentential’ approach to use this coarse lexical resource from a multilingual topic model. Our coarse lexical resource when injected with a parallel corpus outperforms a system trained using parallel corpus and a good quality lexical resource. As demonstrated by the quality of our coarse lexical resource and its benefit to MT, we believe that our sentential approach to create such a resource will help MT for resource-constrained languages.</abstract>
<identifier type="citekey">kanojia-etal-2016-thatll</identifier>
<location>
<url>https://aclanthology.org/L16-1349</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>2199</start>
<end>2203</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T That’ll Do Fine!: A Coarse Lexical Resource for English-Hindi MT, Using Polylingual Topic Models
%A Kanojia, Diptesh
%A Joshi, Aditya
%A Bhattacharyya, Pushpak
%A Carman, Mark James
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F kanojia-etal-2016-thatll
%X Parallel corpora are often injected with bilingual lexical resources for improved Indian language machine translation (MT). In absence of such lexical resources, multilingual topic models have been used to create coarse lexical resources in the past, using a Cartesian product approach. Our results show that for morphologically rich languages like Hindi, the Cartesian product approach is detrimental for MT. We then present a novel ‘sentential’ approach to use this coarse lexical resource from a multilingual topic model. Our coarse lexical resource when injected with a parallel corpus outperforms a system trained using parallel corpus and a good quality lexical resource. As demonstrated by the quality of our coarse lexical resource and its benefit to MT, we believe that our sentential approach to create such a resource will help MT for resource-constrained languages.
%U https://aclanthology.org/L16-1349
%P 2199-2203
Markdown (Informal)
[That’ll Do Fine!: A Coarse Lexical Resource for English-Hindi MT, Using Polylingual Topic Models](https://aclanthology.org/L16-1349) (Kanojia et al., LREC 2016)
ACL