@inproceedings{nam-etal-2020-effective,
title = "Effective Crowdsourcing of Multiple Tasks for Comprehensive Knowledge Extraction",
author = "Nam, Sangha and
Lee, Minho and
Kim, Donghwan and
Han, Kijong and
Kim, Kuntae and
Yoon, Sooji and
Kim, Eun-kyung and
Choi, Key-Sun",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.27",
pages = "212--219",
abstract = "Information extraction from unstructured texts plays a vital role in the field of natural language processing. Although there has been extensive research into each information extraction task (i.e., entity linking, coreference resolution, and relation extraction), data are not available for a continuous and coherent evaluation of all information extraction tasks in a comprehensive framework. Given that each task is performed and evaluated with a different dataset, analyzing the effect of the previous task on the next task with a single dataset throughout the information extraction process is impossible. This paper aims to propose a Korean information extraction initiative point and promote research in this field by presenting crowdsourcing data collected for four information extraction tasks from the same corpus and the training and evaluation results for each task of a state-of-the-art model. These machine learning data for Korean information extraction are the first of their kind, and there are plans to continuously increase the data volume. The test results will serve as an initiative result for each Korean information extraction task and are expected to serve as a comparison target for various studies on Korean information extraction using the data collected in this study.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nam-etal-2020-effective">
<titleInfo>
<title>Effective Crowdsourcing of Multiple Tasks for Comprehensive Knowledge Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sangha</namePart>
<namePart type="family">Nam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minho</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Donghwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kijong</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kuntae</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sooji</namePart>
<namePart type="family">Yoon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eun-kyung</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Information extraction from unstructured texts plays a vital role in the field of natural language processing. Although there has been extensive research into each information extraction task (i.e., entity linking, coreference resolution, and relation extraction), data are not available for a continuous and coherent evaluation of all information extraction tasks in a comprehensive framework. Given that each task is performed and evaluated with a different dataset, analyzing the effect of the previous task on the next task with a single dataset throughout the information extraction process is impossible. This paper aims to propose a Korean information extraction initiative point and promote research in this field by presenting crowdsourcing data collected for four information extraction tasks from the same corpus and the training and evaluation results for each task of a state-of-the-art model. These machine learning data for Korean information extraction are the first of their kind, and there are plans to continuously increase the data volume. The test results will serve as an initiative result for each Korean information extraction task and are expected to serve as a comparison target for various studies on Korean information extraction using the data collected in this study.</abstract>
<identifier type="citekey">nam-etal-2020-effective</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.27</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>212</start>
<end>219</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Effective Crowdsourcing of Multiple Tasks for Comprehensive Knowledge Extraction
%A Nam, Sangha
%A Lee, Minho
%A Kim, Donghwan
%A Han, Kijong
%A Kim, Kuntae
%A Yoon, Sooji
%A Kim, Eun-kyung
%A Choi, Key-Sun
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F nam-etal-2020-effective
%X Information extraction from unstructured texts plays a vital role in the field of natural language processing. Although there has been extensive research into each information extraction task (i.e., entity linking, coreference resolution, and relation extraction), data are not available for a continuous and coherent evaluation of all information extraction tasks in a comprehensive framework. Given that each task is performed and evaluated with a different dataset, analyzing the effect of the previous task on the next task with a single dataset throughout the information extraction process is impossible. This paper aims to propose a Korean information extraction initiative point and promote research in this field by presenting crowdsourcing data collected for four information extraction tasks from the same corpus and the training and evaluation results for each task of a state-of-the-art model. These machine learning data for Korean information extraction are the first of their kind, and there are plans to continuously increase the data volume. The test results will serve as an initiative result for each Korean information extraction task and are expected to serve as a comparison target for various studies on Korean information extraction using the data collected in this study.
%U https://aclanthology.org/2020.lrec-1.27
%P 212-219
Markdown (Informal)
[Effective Crowdsourcing of Multiple Tasks for Comprehensive Knowledge Extraction](https://aclanthology.org/2020.lrec-1.27) (Nam et al., LREC 2020)
ACL
- Sangha Nam, Minho Lee, Donghwan Kim, Kijong Han, Kuntae Kim, Sooji Yoon, Eun-kyung Kim, and Key-Sun Choi. 2020. Effective Crowdsourcing of Multiple Tasks for Comprehensive Knowledge Extraction. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 212–219, Marseille, France. European Language Resources Association.