@inproceedings{bhingardive-etal-2016-synset,
title = "Synset Ranking of {H}indi {W}ord{N}et",
author = "Bhingardive, Sudha and
Shukla, Rajita and
Saraswati, Jaya and
Kashyap, Laxmi and
Singh, Dhirendra 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/L16-1485",
pages = "3039--3043",
abstract = "Word Sense Disambiguation (WSD) is one of the open problems in the area of natural language processing. Various supervised, unsupervised and knowledge based approaches have been proposed for automatically determining the sense of a word in a particular context. It has been observed that such approaches often find it difficult to beat the WordNet First Sense (WFS) baseline which assigns the sense irrespective of context. In this paper, we present our work on creating the WFS baseline for Hindi language by manually ranking the synsets of Hindi WordNet. A ranking tool is developed where human experts can see the frequency of the word senses in the sense-tagged corpora and have been asked to rank the senses of a word by using this information and also his/her intuition. The accuracy of WFS baseline is tested on several standard datasets. F-score is found to be 60{\%}, 65{\%} and 55{\%} on Health, Tourism and News datasets respectively. The created rankings can also be used in other NLP applications viz., Machine Translation, Information Retrieval, Text Summarization, etc.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhingardive-etal-2016-synset">
<titleInfo>
<title>Synset Ranking of Hindi WordNet</title>
</titleInfo>
<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">Rajita</namePart>
<namePart type="family">Shukla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaya</namePart>
<namePart type="family">Saraswati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laxmi</namePart>
<namePart type="family">Kashyap</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">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>Word Sense Disambiguation (WSD) is one of the open problems in the area of natural language processing. Various supervised, unsupervised and knowledge based approaches have been proposed for automatically determining the sense of a word in a particular context. It has been observed that such approaches often find it difficult to beat the WordNet First Sense (WFS) baseline which assigns the sense irrespective of context. In this paper, we present our work on creating the WFS baseline for Hindi language by manually ranking the synsets of Hindi WordNet. A ranking tool is developed where human experts can see the frequency of the word senses in the sense-tagged corpora and have been asked to rank the senses of a word by using this information and also his/her intuition. The accuracy of WFS baseline is tested on several standard datasets. F-score is found to be 60%, 65% and 55% on Health, Tourism and News datasets respectively. The created rankings can also be used in other NLP applications viz., Machine Translation, Information Retrieval, Text Summarization, etc.</abstract>
<identifier type="citekey">bhingardive-etal-2016-synset</identifier>
<location>
<url>https://aclanthology.org/L16-1485</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>3039</start>
<end>3043</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Synset Ranking of Hindi WordNet
%A Bhingardive, Sudha
%A Shukla, Rajita
%A Saraswati, Jaya
%A Kashyap, Laxmi
%A Singh, Dhirendra
%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 bhingardive-etal-2016-synset
%X Word Sense Disambiguation (WSD) is one of the open problems in the area of natural language processing. Various supervised, unsupervised and knowledge based approaches have been proposed for automatically determining the sense of a word in a particular context. It has been observed that such approaches often find it difficult to beat the WordNet First Sense (WFS) baseline which assigns the sense irrespective of context. In this paper, we present our work on creating the WFS baseline for Hindi language by manually ranking the synsets of Hindi WordNet. A ranking tool is developed where human experts can see the frequency of the word senses in the sense-tagged corpora and have been asked to rank the senses of a word by using this information and also his/her intuition. The accuracy of WFS baseline is tested on several standard datasets. F-score is found to be 60%, 65% and 55% on Health, Tourism and News datasets respectively. The created rankings can also be used in other NLP applications viz., Machine Translation, Information Retrieval, Text Summarization, etc.
%U https://aclanthology.org/L16-1485
%P 3039-3043
Markdown (Informal)
[Synset Ranking of Hindi WordNet](https://aclanthology.org/L16-1485) (Bhingardive et al., LREC 2016)
ACL
- Sudha Bhingardive, Rajita Shukla, Jaya Saraswati, Laxmi Kashyap, Dhirendra Singh, and Pushpak Bhattacharyya. 2016. Synset Ranking of Hindi WordNet. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 3039–3043, Portorož, Slovenia. European Language Resources Association (ELRA).