@inproceedings{segura-bedmar-etal-2017-labda,
title = "{LABDA} at {S}em{E}val-2017 Task 10: Extracting Keyphrases from Scientific Publications by combining the {BANNER} tool and the {UMLS} Semantic Network",
author = "Segura-Bedmar, Isabel and
Col{\'o}n-Ruiz, Crist{\'o}bal and
Mart{\'\i}nez, Paloma",
editor = "Bethard, Steven and
Carpuat, Marine and
Apidianaki, Marianna and
Mohammad, Saif M. and
Cer, Daniel and
Jurgens, David",
booktitle = "Proceedings of the 11th International Workshop on Semantic Evaluation ({S}em{E}val-2017)",
month = aug,
year = "2017",
address = "Vancouver, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/S17-2164",
doi = "10.18653/v1/S17-2164",
pages = "947--950",
abstract = "This paper describes the system presented by the LABDA group at SemEval 2017 Task 10 ScienceIE, specifically for the subtasks of identification and classification of keyphrases from scientific articles. For the task of identification, we use the BANNER tool, a named entity recognition system, which is based on conditional random fields (CRF) and has obtained successful results in the biomedical domain. To classify keyphrases, we study the UMLS semantic network and propose a possible linking between the keyphrase types and the UMLS semantic groups. Based on this semantic linking, we create a dictionary for each keyphrase type. Then, a feature indicating if a token is found in one of these dictionaries is incorporated to feature set used by the BANNER tool. The final results on the test dataset show that our system still needs to be improved, but the conditional random fields and, consequently, the BANNER system can be used as a first approximation to identify and classify keyphrases.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="segura-bedmar-etal-2017-labda">
<titleInfo>
<title>LABDA at SemEval-2017 Task 10: Extracting Keyphrases from Scientific Publications by combining the BANNER tool and the UMLS Semantic Network</title>
</titleInfo>
<name type="personal">
<namePart type="given">Isabel</namePart>
<namePart type="family">Segura-Bedmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristóbal</namePart>
<namePart type="family">Colón-Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paloma</namePart>
<namePart type="family">Martínez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saif</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Mohammad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Cer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vancouver, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the system presented by the LABDA group at SemEval 2017 Task 10 ScienceIE, specifically for the subtasks of identification and classification of keyphrases from scientific articles. For the task of identification, we use the BANNER tool, a named entity recognition system, which is based on conditional random fields (CRF) and has obtained successful results in the biomedical domain. To classify keyphrases, we study the UMLS semantic network and propose a possible linking between the keyphrase types and the UMLS semantic groups. Based on this semantic linking, we create a dictionary for each keyphrase type. Then, a feature indicating if a token is found in one of these dictionaries is incorporated to feature set used by the BANNER tool. The final results on the test dataset show that our system still needs to be improved, but the conditional random fields and, consequently, the BANNER system can be used as a first approximation to identify and classify keyphrases.</abstract>
<identifier type="citekey">segura-bedmar-etal-2017-labda</identifier>
<identifier type="doi">10.18653/v1/S17-2164</identifier>
<location>
<url>https://aclanthology.org/S17-2164</url>
</location>
<part>
<date>2017-08</date>
<extent unit="page">
<start>947</start>
<end>950</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LABDA at SemEval-2017 Task 10: Extracting Keyphrases from Scientific Publications by combining the BANNER tool and the UMLS Semantic Network
%A Segura-Bedmar, Isabel
%A Colón-Ruiz, Cristóbal
%A Martínez, Paloma
%Y Bethard, Steven
%Y Carpuat, Marine
%Y Apidianaki, Marianna
%Y Mohammad, Saif M.
%Y Cer, Daniel
%Y Jurgens, David
%S Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)
%D 2017
%8 August
%I Association for Computational Linguistics
%C Vancouver, Canada
%F segura-bedmar-etal-2017-labda
%X This paper describes the system presented by the LABDA group at SemEval 2017 Task 10 ScienceIE, specifically for the subtasks of identification and classification of keyphrases from scientific articles. For the task of identification, we use the BANNER tool, a named entity recognition system, which is based on conditional random fields (CRF) and has obtained successful results in the biomedical domain. To classify keyphrases, we study the UMLS semantic network and propose a possible linking between the keyphrase types and the UMLS semantic groups. Based on this semantic linking, we create a dictionary for each keyphrase type. Then, a feature indicating if a token is found in one of these dictionaries is incorporated to feature set used by the BANNER tool. The final results on the test dataset show that our system still needs to be improved, but the conditional random fields and, consequently, the BANNER system can be used as a first approximation to identify and classify keyphrases.
%R 10.18653/v1/S17-2164
%U https://aclanthology.org/S17-2164
%U https://doi.org/10.18653/v1/S17-2164
%P 947-950
Markdown (Informal)
[LABDA at SemEval-2017 Task 10: Extracting Keyphrases from Scientific Publications by combining the BANNER tool and the UMLS Semantic Network](https://aclanthology.org/S17-2164) (Segura-Bedmar et al., SemEval 2017)
ACL