@inproceedings{el-haj-etal-2017-creating,
title = "Creating and Validating Multilingual Semantic Representations for Six Languages: Expert versus Non-Expert Crowds",
author = "El-Haj, Mahmoud and
Rayson, Paul and
Piao, Scott and
Wattam, Stephen",
editor = "Camacho-Collados, Jose and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 1st Workshop on Sense, Concept and Entity Representations and their Applications",
month = apr,
year = "2017",
address = "Valencia, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-1908",
doi = "10.18653/v1/W17-1908",
pages = "61--71",
abstract = "Creating high-quality wide-coverage multilingual semantic lexicons to support knowledge-based approaches is a challenging time-consuming manual task. This has traditionally been performed by linguistic experts: a slow and expensive process. We present an experiment in which we adapt and evaluate crowdsourcing methods employing native speakers to generate a list of coarse-grained senses under a common multilingual semantic taxonomy for sets of words in six languages. 451 non-experts (including 427 Mechanical Turk workers) and 15 expert participants semantically annotated 250 words manually for Arabic, Chinese, English, Italian, Portuguese and Urdu lexicons. In order to avoid erroneous (spam) crowdsourced results, we used a novel task-specific two-phase filtering process where users were asked to identify synonyms in the target language, and remove erroneous senses.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="el-haj-etal-2017-creating">
<titleInfo>
<title>Creating and Validating Multilingual Semantic Representations for Six Languages: Expert versus Non-Expert Crowds</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mahmoud</namePart>
<namePart type="family">El-Haj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="family">Piao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="family">Wattam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Sense, Concept and Entity Representations and their Applications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jose</namePart>
<namePart type="family">Camacho-Collados</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Valencia, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Creating high-quality wide-coverage multilingual semantic lexicons to support knowledge-based approaches is a challenging time-consuming manual task. This has traditionally been performed by linguistic experts: a slow and expensive process. We present an experiment in which we adapt and evaluate crowdsourcing methods employing native speakers to generate a list of coarse-grained senses under a common multilingual semantic taxonomy for sets of words in six languages. 451 non-experts (including 427 Mechanical Turk workers) and 15 expert participants semantically annotated 250 words manually for Arabic, Chinese, English, Italian, Portuguese and Urdu lexicons. In order to avoid erroneous (spam) crowdsourced results, we used a novel task-specific two-phase filtering process where users were asked to identify synonyms in the target language, and remove erroneous senses.</abstract>
<identifier type="citekey">el-haj-etal-2017-creating</identifier>
<identifier type="doi">10.18653/v1/W17-1908</identifier>
<location>
<url>https://aclanthology.org/W17-1908</url>
</location>
<part>
<date>2017-04</date>
<extent unit="page">
<start>61</start>
<end>71</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Creating and Validating Multilingual Semantic Representations for Six Languages: Expert versus Non-Expert Crowds
%A El-Haj, Mahmoud
%A Rayson, Paul
%A Piao, Scott
%A Wattam, Stephen
%Y Camacho-Collados, Jose
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 1st Workshop on Sense, Concept and Entity Representations and their Applications
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F el-haj-etal-2017-creating
%X Creating high-quality wide-coverage multilingual semantic lexicons to support knowledge-based approaches is a challenging time-consuming manual task. This has traditionally been performed by linguistic experts: a slow and expensive process. We present an experiment in which we adapt and evaluate crowdsourcing methods employing native speakers to generate a list of coarse-grained senses under a common multilingual semantic taxonomy for sets of words in six languages. 451 non-experts (including 427 Mechanical Turk workers) and 15 expert participants semantically annotated 250 words manually for Arabic, Chinese, English, Italian, Portuguese and Urdu lexicons. In order to avoid erroneous (spam) crowdsourced results, we used a novel task-specific two-phase filtering process where users were asked to identify synonyms in the target language, and remove erroneous senses.
%R 10.18653/v1/W17-1908
%U https://aclanthology.org/W17-1908
%U https://doi.org/10.18653/v1/W17-1908
%P 61-71
Markdown (Informal)
[Creating and Validating Multilingual Semantic Representations for Six Languages: Expert versus Non-Expert Crowds](https://aclanthology.org/W17-1908) (El-Haj et al., SENSE 2017)
ACL