NLP Questions Answering Using DBpedia and YAGO
In this paper, we present results of employing DBpedia and YAGO as lexical databases for answering questions formulated in the natural language. The proposed solution has been evaluated for answering class 1 and class 2 questions (out of 5 classes defined by Moldovan for TREC conference). Our method...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
World Scientific Publishing
2020-11-01
|
| Series: | Vietnam Journal of Computer Science |
| Subjects: | |
| Online Access: | http://www.worldscientific.com/doi/pdf/10.1142/S2196888820500190 |
| _version_ | 1818239690761830400 |
|---|---|
| author | Tomasz Boiński Julian Szymański Bartłomiej Dudek Paweł Zalewski Szymon Dompke Maria Czarnecka |
| author_facet | Tomasz Boiński Julian Szymański Bartłomiej Dudek Paweł Zalewski Szymon Dompke Maria Czarnecka |
| author_sort | Tomasz Boiński |
| collection | DOAJ |
| description | In this paper, we present results of employing DBpedia and YAGO as lexical databases for answering questions formulated in the natural language. The proposed solution has been evaluated for answering class 1 and class 2 questions (out of 5 classes defined by Moldovan for TREC conference). Our method uses dependency trees generated from the user query. The trees are browsed for paths leading from the root of the tree to the question subject. We call those paths fibers and they represent the user intention. The question analysis consists of three stages: query analysis, query breakdown and information retrieval. The aim of those stages is the detection of the entities of interest and its attributes, indicating the users’ domain of interest. The user query is then converted into a SPARQL query and sent to the DBpedia and YAGO databases. The baseline and the extended methods are presented and the quality of the solution is evaluated and discussed. |
| first_indexed | 2024-12-12T13:01:34Z |
| format | Article |
| id | doaj.art-32dbd73e14b84a96aedb5589cf3b183b |
| institution | Directory Open Access Journal |
| issn | 2196-8888 2196-8896 |
| language | English |
| last_indexed | 2024-12-12T13:01:34Z |
| publishDate | 2020-11-01 |
| publisher | World Scientific Publishing |
| record_format | Article |
| series | Vietnam Journal of Computer Science |
| spelling | doaj.art-32dbd73e14b84a96aedb5589cf3b183b2022-12-22T00:23:46ZengWorld Scientific PublishingVietnam Journal of Computer Science2196-88882196-88962020-11-017433935410.1142/S219688882050019010.1142/S2196888820500190NLP Questions Answering Using DBpedia and YAGOTomasz Boiński0Julian Szymański1Bartłomiej Dudek2Paweł Zalewski3Szymon Dompke4Maria Czarnecka5Department of Computer Architecture, Faculty of Electronics, Telecommunication and Informatics, Gdańsk University of Technology, 11/12 Narutowicza Street, Gdańsk 80-180, PolandDepartment of Computer Architecture, Faculty of Electronics, Telecommunication and Informatics, Gdańsk University of Technology, 11/12 Narutowicza Street, Gdańsk 80-180, PolandDepartment of Computer Architecture, Faculty of Electronics, Telecommunication and Informatics, Gdańsk University of Technology, 11/12 Narutowicza Street, Gdańsk 80-180, PolandDepartment of Computer Architecture, Faculty of Electronics, Telecommunication and Informatics, Gdańsk University of Technology, 11/12 Narutowicza Street, Gdańsk 80-180, PolandDepartment of Computer Architecture, Faculty of Electronics, Telecommunication and Informatics, Gdańsk University of Technology, 11/12 Narutowicza Street, Gdańsk 80-180, PolandDepartment of Computer Architecture, Faculty of Electronics, Telecommunication and Informatics, Gdańsk University of Technology, 11/12 Narutowicza Street, Gdańsk 80-180, PolandIn this paper, we present results of employing DBpedia and YAGO as lexical databases for answering questions formulated in the natural language. The proposed solution has been evaluated for answering class 1 and class 2 questions (out of 5 classes defined by Moldovan for TREC conference). Our method uses dependency trees generated from the user query. The trees are browsed for paths leading from the root of the tree to the question subject. We call those paths fibers and they represent the user intention. The question analysis consists of three stages: query analysis, query breakdown and information retrieval. The aim of those stages is the detection of the entities of interest and its attributes, indicating the users’ domain of interest. The user query is then converted into a SPARQL query and sent to the DBpedia and YAGO databases. The baseline and the extended methods are presented and the quality of the solution is evaluated and discussed.http://www.worldscientific.com/doi/pdf/10.1142/S2196888820500190question answeringnlpyagodbpedia |
| spellingShingle | Tomasz Boiński Julian Szymański Bartłomiej Dudek Paweł Zalewski Szymon Dompke Maria Czarnecka NLP Questions Answering Using DBpedia and YAGO Vietnam Journal of Computer Science question answering nlp yago dbpedia |
| title | NLP Questions Answering Using DBpedia and YAGO |
| title_full | NLP Questions Answering Using DBpedia and YAGO |
| title_fullStr | NLP Questions Answering Using DBpedia and YAGO |
| title_full_unstemmed | NLP Questions Answering Using DBpedia and YAGO |
| title_short | NLP Questions Answering Using DBpedia and YAGO |
| title_sort | nlp questions answering using dbpedia and yago |
| topic | question answering nlp yago dbpedia |
| url | http://www.worldscientific.com/doi/pdf/10.1142/S2196888820500190 |
| work_keys_str_mv | AT tomaszboinski nlpquestionsansweringusingdbpediaandyago AT julianszymanski nlpquestionsansweringusingdbpediaandyago AT bartłomiejdudek nlpquestionsansweringusingdbpediaandyago AT pawełzalewski nlpquestionsansweringusingdbpediaandyago AT szymondompke nlpquestionsansweringusingdbpediaandyago AT mariaczarnecka nlpquestionsansweringusingdbpediaandyago |