Issues and challenges in semantic question answering through natural language interface.

Semantic question answering demand different processing compared to the common information retrieval based question answering method because the semantic knowledge base is stored in the triples form. However, manipulating the knowledge requires understanding its structure and proficiency in semanti...

Full description

Bibliographic Details
Main Authors: Mohd Sharef, Nurfadhlina, Mohd Noah, Shahrul Azman, Azmi Murad, Masrah Azrifah
Format: Article
Language:English
English
Published: Advanced Institute of Convergence Information Technology 2013
Online Access:http://psasir.upm.edu.my/id/eprint/30615/1/Issues%20and%20challenges%20in%20semantic%20question%20answering%20through%20natural%20language%20interface.pdf
_version_ 1825947741663002624
author Mohd Sharef, Nurfadhlina
Mohd Noah, Shahrul Azman
Azmi Murad, Masrah Azrifah
author_facet Mohd Sharef, Nurfadhlina
Mohd Noah, Shahrul Azman
Azmi Murad, Masrah Azrifah
author_sort Mohd Sharef, Nurfadhlina
collection UPM
description Semantic question answering demand different processing compared to the common information retrieval based question answering method because the semantic knowledge base is stored in the triples form. However, manipulating the knowledge requires understanding its structure and proficiency in semantic query language such as SPARQL. Natural language interface alleviates this by allowing user to input question in their human language and produce an answer by translating the input into an equivalent SPARQL before it is executed to retrieve the answer. However, several challenges exist such as concept identification, compatible ontology triple construction and semantic mapping. Existing studies have focused mainly on the semantic disambiguation such as through consolidation where user interaction is initiated so that relevant concept can be chosen by the user to be inserted into the SPARQL. In this paper we focus on the linguistic challenge in NLI, specifically on the question complexity depth, processes that need to be performed to answer the question and gaps in existing study. It is concluded that more works are in demand to process complex questions such that involve multi-variables and multi-triples. Besides the issues posed by the answer generation for the combined sub-questions in the composite question, the challenges faced by the simple question is also inherited which requires an application that is robust in ontology concept annotation. This will ensure that the translated query would capture entirely the expression in the original question and accurate answer will be returned.
first_indexed 2024-03-06T08:18:06Z
format Article
id upm.eprints-30615
institution Universiti Putra Malaysia
language English
English
last_indexed 2024-03-06T08:18:06Z
publishDate 2013
publisher Advanced Institute of Convergence Information Technology
record_format dspace
spelling upm.eprints-306152015-10-07T01:42:42Z http://psasir.upm.edu.my/id/eprint/30615/ Issues and challenges in semantic question answering through natural language interface. Mohd Sharef, Nurfadhlina Mohd Noah, Shahrul Azman Azmi Murad, Masrah Azrifah Semantic question answering demand different processing compared to the common information retrieval based question answering method because the semantic knowledge base is stored in the triples form. However, manipulating the knowledge requires understanding its structure and proficiency in semantic query language such as SPARQL. Natural language interface alleviates this by allowing user to input question in their human language and produce an answer by translating the input into an equivalent SPARQL before it is executed to retrieve the answer. However, several challenges exist such as concept identification, compatible ontology triple construction and semantic mapping. Existing studies have focused mainly on the semantic disambiguation such as through consolidation where user interaction is initiated so that relevant concept can be chosen by the user to be inserted into the SPARQL. In this paper we focus on the linguistic challenge in NLI, specifically on the question complexity depth, processes that need to be performed to answer the question and gaps in existing study. It is concluded that more works are in demand to process complex questions such that involve multi-variables and multi-triples. Besides the issues posed by the answer generation for the combined sub-questions in the composite question, the challenges faced by the simple question is also inherited which requires an application that is robust in ontology concept annotation. This will ensure that the translated query would capture entirely the expression in the original question and accurate answer will be returned. Advanced Institute of Convergence Information Technology 2013-09 Article PeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/30615/1/Issues%20and%20challenges%20in%20semantic%20question%20answering%20through%20natural%20language%20interface.pdf Mohd Sharef, Nurfadhlina and Mohd Noah, Shahrul Azman and Azmi Murad, Masrah Azrifah (2013) Issues and challenges in semantic question answering through natural language interface. Journal of Next Generation Information Technology, 4 (7). pp. 50-60. ISSN 2092-8637; ESSN: 2233-9388 English
spellingShingle Mohd Sharef, Nurfadhlina
Mohd Noah, Shahrul Azman
Azmi Murad, Masrah Azrifah
Issues and challenges in semantic question answering through natural language interface.
title Issues and challenges in semantic question answering through natural language interface.
title_full Issues and challenges in semantic question answering through natural language interface.
title_fullStr Issues and challenges in semantic question answering through natural language interface.
title_full_unstemmed Issues and challenges in semantic question answering through natural language interface.
title_short Issues and challenges in semantic question answering through natural language interface.
title_sort issues and challenges in semantic question answering through natural language interface
url http://psasir.upm.edu.my/id/eprint/30615/1/Issues%20and%20challenges%20in%20semantic%20question%20answering%20through%20natural%20language%20interface.pdf
work_keys_str_mv AT mohdsharefnurfadhlina issuesandchallengesinsemanticquestionansweringthroughnaturallanguageinterface
AT mohdnoahshahrulazman issuesandchallengesinsemanticquestionansweringthroughnaturallanguageinterface
AT azmimuradmasrahazrifah issuesandchallengesinsemanticquestionansweringthroughnaturallanguageinterface