@inproceedings{bekavac-snajder-2016-graph,
title = "Graph-Based Induction of Word Senses in {C}roatian",
author = "Bekavac, Marko and
{\v{S}}najder, Jan",
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/L16-1481",
pages = "3014--3018",
abstract = "Word sense induction (WSI) seeks to induce senses of words from unannotated corpora. In this paper, we address the WSI task for the Croatian language. We adopt the word clustering approach based on co-occurrence graphs, in which senses are taken to correspond to strongly inter-connected components of co-occurring words. We experiment with a number of graph construction techniques and clustering algorithms, and evaluate the sense inventories both as a clustering problem and extrinsically on a word sense disambiguation (WSD) task. In the cluster-based evaluation, Chinese Whispers algorithm outperformed Markov Clustering, yielding a normalized mutual information score of 64.3. In contrast, in WSD evaluation Markov Clustering performed better, yielding an accuracy of about 75{\%}. We are making available two induced sense inventories of 10,000 most frequent Croatian words: one coarse-grained and one fine-grained inventory, both obtained using the Markov Clustering algorithm.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bekavac-snajder-2016-graph">
<titleInfo>
<title>Graph-Based Induction of Word Senses in Croatian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Bekavac</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Šnajder</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 induction (WSI) seeks to induce senses of words from unannotated corpora. In this paper, we address the WSI task for the Croatian language. We adopt the word clustering approach based on co-occurrence graphs, in which senses are taken to correspond to strongly inter-connected components of co-occurring words. We experiment with a number of graph construction techniques and clustering algorithms, and evaluate the sense inventories both as a clustering problem and extrinsically on a word sense disambiguation (WSD) task. In the cluster-based evaluation, Chinese Whispers algorithm outperformed Markov Clustering, yielding a normalized mutual information score of 64.3. In contrast, in WSD evaluation Markov Clustering performed better, yielding an accuracy of about 75%. We are making available two induced sense inventories of 10,000 most frequent Croatian words: one coarse-grained and one fine-grained inventory, both obtained using the Markov Clustering algorithm.</abstract>
<identifier type="citekey">bekavac-snajder-2016-graph</identifier>
<location>
<url>https://aclanthology.org/L16-1481</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>3014</start>
<end>3018</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Graph-Based Induction of Word Senses in Croatian
%A Bekavac, Marko
%A Šnajder, Jan
%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 bekavac-snajder-2016-graph
%X Word sense induction (WSI) seeks to induce senses of words from unannotated corpora. In this paper, we address the WSI task for the Croatian language. We adopt the word clustering approach based on co-occurrence graphs, in which senses are taken to correspond to strongly inter-connected components of co-occurring words. We experiment with a number of graph construction techniques and clustering algorithms, and evaluate the sense inventories both as a clustering problem and extrinsically on a word sense disambiguation (WSD) task. In the cluster-based evaluation, Chinese Whispers algorithm outperformed Markov Clustering, yielding a normalized mutual information score of 64.3. In contrast, in WSD evaluation Markov Clustering performed better, yielding an accuracy of about 75%. We are making available two induced sense inventories of 10,000 most frequent Croatian words: one coarse-grained and one fine-grained inventory, both obtained using the Markov Clustering algorithm.
%U https://aclanthology.org/L16-1481
%P 3014-3018
Markdown (Informal)
[Graph-Based Induction of Word Senses in Croatian](https://aclanthology.org/L16-1481) (Bekavac & Šnajder, LREC 2016)
ACL
- Marko Bekavac and Jan Šnajder. 2016. Graph-Based Induction of Word Senses in Croatian. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 3014–3018, Portorož, Slovenia. European Language Resources Association (ELRA).