@inproceedings{kiselev-etal-2016-eliminating,
title = "Eliminating Fuzzy Duplicates in Crowdsourced Lexical Resources",
author = "Kiselev, Yuri and
Ustalov, Dmitry and
Porshnev, Sergey",
editor = "Fellbaum, Christiane and
Vossen, Piek and
Mititelu, Verginica Barbu and
Forascu, Corina",
booktitle = "Proceedings of the 8th Global WordNet Conference (GWC)",
month = "27--30 " # jan,
year = "2016",
address = "Bucharest, Romania",
publisher = "Global Wordnet Association",
url = "https://aclanthology.org/2016.gwc-1.25",
pages = "162--168",
abstract = "Collaboratively created lexical resources is a trending approach to creating high quality thesauri in a short time span at a remarkably low price. The key idea is to invite non-expert participants to express and share their knowledge with the aim of constructing a resource. However, this approach tends to be noisy and error-prone, thus making data cleansing a highly topical task to perform. In this paper, we study different techniques for synset deduplication including machine- and crowd-based ones. Eventually, we put forward an approach that can solve the deduplication problem fully automatically, with the quality comparable to the expert-based approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kiselev-etal-2016-eliminating">
<titleInfo>
<title>Eliminating Fuzzy Duplicates in Crowdsourced Lexical Resources</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuri</namePart>
<namePart type="family">Kiselev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dmitry</namePart>
<namePart type="family">Ustalov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sergey</namePart>
<namePart type="family">Porshnev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-27–30 jan</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Global WordNet Conference (GWC)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christiane</namePart>
<namePart type="family">Fellbaum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piek</namePart>
<namePart type="family">Vossen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Verginica</namePart>
<namePart type="given">Barbu</namePart>
<namePart type="family">Mititelu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Corina</namePart>
<namePart type="family">Forascu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Global Wordnet Association</publisher>
<place>
<placeTerm type="text">Bucharest, Romania</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Collaboratively created lexical resources is a trending approach to creating high quality thesauri in a short time span at a remarkably low price. The key idea is to invite non-expert participants to express and share their knowledge with the aim of constructing a resource. However, this approach tends to be noisy and error-prone, thus making data cleansing a highly topical task to perform. In this paper, we study different techniques for synset deduplication including machine- and crowd-based ones. Eventually, we put forward an approach that can solve the deduplication problem fully automatically, with the quality comparable to the expert-based approach.</abstract>
<identifier type="citekey">kiselev-etal-2016-eliminating</identifier>
<location>
<url>https://aclanthology.org/2016.gwc-1.25</url>
</location>
<part>
<date>2016-27–30 jan</date>
<extent unit="page">
<start>162</start>
<end>168</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Eliminating Fuzzy Duplicates in Crowdsourced Lexical Resources
%A Kiselev, Yuri
%A Ustalov, Dmitry
%A Porshnev, Sergey
%Y Fellbaum, Christiane
%Y Vossen, Piek
%Y Mititelu, Verginica Barbu
%Y Forascu, Corina
%S Proceedings of the 8th Global WordNet Conference (GWC)
%D 2016
%8 27–30 jan
%I Global Wordnet Association
%C Bucharest, Romania
%F kiselev-etal-2016-eliminating
%X Collaboratively created lexical resources is a trending approach to creating high quality thesauri in a short time span at a remarkably low price. The key idea is to invite non-expert participants to express and share their knowledge with the aim of constructing a resource. However, this approach tends to be noisy and error-prone, thus making data cleansing a highly topical task to perform. In this paper, we study different techniques for synset deduplication including machine- and crowd-based ones. Eventually, we put forward an approach that can solve the deduplication problem fully automatically, with the quality comparable to the expert-based approach.
%U https://aclanthology.org/2016.gwc-1.25
%P 162-168
Markdown (Informal)
[Eliminating Fuzzy Duplicates in Crowdsourced Lexical Resources](https://aclanthology.org/2016.gwc-1.25) (Kiselev et al., GWC 2016)
ACL