@inproceedings{de-boer-verhoosel-2020-towards,
title = "Towards Data-driven Ontologies: a Filtering Approach using Keywords and Natural Language Constructs",
author = "de Boer, Maaike and
Verhoosel, Jack P. C.",
booktitle = "Proceedings of the 12th Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.278",
pages = "2285--2292",
abstract = "Creating ontologies is an expensive task. Our vision is that we can automatically generate ontologies based on a set of relevant documents to create a kick-start in ontology creating sessions. In this paper, we focus on enhancing two often used methods, OpenIE and co-occurrences. We evaluate the methods on two document sets, one about pizza and one about the agriculture domain. The methods are evaluated using two types of F1-score (objective, quantitative) and through a human assessment (subjective, qualitative). The results show that 1) Cooc performs both objectively and subjectively better than OpenIE; 2) the filtering methods based on keywords and on Word2vec perform similarly; 3) the filtering methods both perform better compared to OpenIE and similar to Cooc; 4) Cooc-NVP performs best, especially considering the subjective evaluation. Although, the investigated methods provide a good start for extracting an ontology out of a set of domain documents, various improvements are still possible, especially in the natural language based methods.",
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="de-boer-verhoosel-2020-towards">
<titleInfo>
<title>Towards Data-driven Ontologies: a Filtering Approach using Keywords and Natural Language Constructs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maaike</namePart>
<namePart type="family">de Boer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jack</namePart>
<namePart type="given">P</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Verhoosel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-may</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 12th Language Resources and Evaluation Conference</title>
</titleInfo>
<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>Creating ontologies is an expensive task. Our vision is that we can automatically generate ontologies based on a set of relevant documents to create a kick-start in ontology creating sessions. In this paper, we focus on enhancing two often used methods, OpenIE and co-occurrences. We evaluate the methods on two document sets, one about pizza and one about the agriculture domain. The methods are evaluated using two types of F1-score (objective, quantitative) and through a human assessment (subjective, qualitative). The results show that 1) Cooc performs both objectively and subjectively better than OpenIE; 2) the filtering methods based on keywords and on Word2vec perform similarly; 3) the filtering methods both perform better compared to OpenIE and similar to Cooc; 4) Cooc-NVP performs best, especially considering the subjective evaluation. Although, the investigated methods provide a good start for extracting an ontology out of a set of domain documents, various improvements are still possible, especially in the natural language based methods.</abstract>
<identifier type="citekey">de-boer-verhoosel-2020-towards</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.278</url>
</location>
<part>
<date>2020-may</date>
<extent unit="page">
<start>2285</start>
<end>2292</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Data-driven Ontologies: a Filtering Approach using Keywords and Natural Language Constructs
%A de Boer, Maaike
%A Verhoosel, Jack P. C.
%S Proceedings of the 12th 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 de-boer-verhoosel-2020-towards
%X Creating ontologies is an expensive task. Our vision is that we can automatically generate ontologies based on a set of relevant documents to create a kick-start in ontology creating sessions. In this paper, we focus on enhancing two often used methods, OpenIE and co-occurrences. We evaluate the methods on two document sets, one about pizza and one about the agriculture domain. The methods are evaluated using two types of F1-score (objective, quantitative) and through a human assessment (subjective, qualitative). The results show that 1) Cooc performs both objectively and subjectively better than OpenIE; 2) the filtering methods based on keywords and on Word2vec perform similarly; 3) the filtering methods both perform better compared to OpenIE and similar to Cooc; 4) Cooc-NVP performs best, especially considering the subjective evaluation. Although, the investigated methods provide a good start for extracting an ontology out of a set of domain documents, various improvements are still possible, especially in the natural language based methods.
%U https://aclanthology.org/2020.lrec-1.278
%P 2285-2292
Markdown (Informal)
[Towards Data-driven Ontologies: a Filtering Approach using Keywords and Natural Language Constructs](https://aclanthology.org/2020.lrec-1.278) (de Boer & Verhoosel, LREC 2020)
ACL