@inproceedings{singh-etal-2016-multiword,
title = "Multiword Expressions Dataset for {I}ndian Languages",
author = "Singh, Dhirendra and
Bhingardive, Sudha and
Bhattacharyya, Pushpak",
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/L16-1369",
pages = "2331--2335",
abstract = "Multiword Expressions (MWEs) are used frequently in natural languages, but understanding the diversity in MWEs is one of the open problem in the area of Natural Language Processing. In the context of Indian languages, MWEs play an important role. In this paper, we present MWEs annotation dataset created for Indian languages viz., Hindi and Marathi. We extract possible MWE candidates using two repositories: 1) the POS-tagged corpus and 2) the IndoWordNet synsets. Annotation is done for two types of MWEs: compound nouns and light verb constructions. In the process of annotation, human annotators tag valid MWEs from these candidates based on the standard guidelines provided to them. We obtained 3178 compound nouns and 2556 light verb constructions in Hindi and 1003 compound nouns and 2416 light verb constructions in Marathi using two repositories mentioned before. This created resource is made available publicly and can be used as a gold standard for Hindi and Marathi MWE systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singh-etal-2016-multiword">
<titleInfo>
<title>Multiword Expressions Dataset for Indian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dhirendra</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sudha</namePart>
<namePart type="family">Bhingardive</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>
<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>Multiword Expressions (MWEs) are used frequently in natural languages, but understanding the diversity in MWEs is one of the open problem in the area of Natural Language Processing. In the context of Indian languages, MWEs play an important role. In this paper, we present MWEs annotation dataset created for Indian languages viz., Hindi and Marathi. We extract possible MWE candidates using two repositories: 1) the POS-tagged corpus and 2) the IndoWordNet synsets. Annotation is done for two types of MWEs: compound nouns and light verb constructions. In the process of annotation, human annotators tag valid MWEs from these candidates based on the standard guidelines provided to them. We obtained 3178 compound nouns and 2556 light verb constructions in Hindi and 1003 compound nouns and 2416 light verb constructions in Marathi using two repositories mentioned before. This created resource is made available publicly and can be used as a gold standard for Hindi and Marathi MWE systems.</abstract>
<identifier type="citekey">singh-etal-2016-multiword</identifier>
<location>
<url>https://aclanthology.org/L16-1369</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>2331</start>
<end>2335</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multiword Expressions Dataset for Indian Languages
%A Singh, Dhirendra
%A Bhingardive, Sudha
%A Bhattacharyya, Pushpak
%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 singh-etal-2016-multiword
%X Multiword Expressions (MWEs) are used frequently in natural languages, but understanding the diversity in MWEs is one of the open problem in the area of Natural Language Processing. In the context of Indian languages, MWEs play an important role. In this paper, we present MWEs annotation dataset created for Indian languages viz., Hindi and Marathi. We extract possible MWE candidates using two repositories: 1) the POS-tagged corpus and 2) the IndoWordNet synsets. Annotation is done for two types of MWEs: compound nouns and light verb constructions. In the process of annotation, human annotators tag valid MWEs from these candidates based on the standard guidelines provided to them. We obtained 3178 compound nouns and 2556 light verb constructions in Hindi and 1003 compound nouns and 2416 light verb constructions in Marathi using two repositories mentioned before. This created resource is made available publicly and can be used as a gold standard for Hindi and Marathi MWE systems.
%U https://aclanthology.org/L16-1369
%P 2331-2335
Markdown (Informal)
[Multiword Expressions Dataset for Indian Languages](https://aclanthology.org/L16-1369) (Singh et al., LREC 2016)
ACL
- Dhirendra Singh, Sudha Bhingardive, and Pushpak Bhattacharyya. 2016. Multiword Expressions Dataset for Indian Languages. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 2331–2335, Portorož, Slovenia. European Language Resources Association (ELRA).