Semantic Querying of News Articles With Natural Language Questions

Semantic Querying of News Articles With Natural Language Questions

Tuan-Dung Cao, Quang-Minh Nguyen
Copyright: © 2021 |Pages: 20
DOI: 10.4018/JITR.2021070103
OnDemand:
(Individual Articles)
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

The heterogeneity and the increasing amount of the news published on the web create challenges in accessing them. In the authors' previous studies, they introduced a semantic web-based sports news aggregation system called BKSport, which manages to generate metadata for every news item. Providing an intuitive and expressive way to retrieve information and exploiting the advantages of semantic search technique is within their consideration. In this paper, they propose a method to transform natural language questions into SPARQL queries, which could be applied to existing semantic data. This method is mainly based on the following tasks: the construction of a semantic model representing a question, detection of ontology vocabularies and knowledge base elements in question, and their mapping to generate a query. Experiments are performed on a set of questions belonging to various categories, and the results show that the proposed method provides high precision.
Article Preview
Top

As SPARQL queries are essential for implementing semantic search in many systems, there were some research works directly used SPARQL statements to query information from data of semantic knowledge store (Zhai & Zhou, 2010). However, the use of SPARQL syntax has some weaknesses such as complex query language syntax. In addition, it requires users to understand inside structure of the semantic knowledge store. Although this language has been extended to take into consideration keywords and wildcards, when users are not experienced with ontology, the approach introduced by (Elbassuoni et al., 2010) still requires them to know the language. Several other research works enhanced user friendliness by providing graphical user interface based on ontology to formulate SPARQL queries (Clemmer & Davies, 2011; Yamaguchi et al., 2014), although they still required users to engage in certain manipulation and basically understand ontology.

Complete Article List

Search this Journal:
Reset
Volume 16: 1 Issue (2024): Forthcoming, Available for Pre-Order
Volume 15: 6 Issues (2022): 1 Released, 5 Forthcoming
Volume 14: 4 Issues (2021)
Volume 13: 4 Issues (2020)
Volume 12: 4 Issues (2019)
Volume 11: 4 Issues (2018)
Volume 10: 4 Issues (2017)
Volume 9: 4 Issues (2016)
Volume 8: 4 Issues (2015)
Volume 7: 4 Issues (2014)
Volume 6: 4 Issues (2013)
Volume 5: 4 Issues (2012)
Volume 4: 4 Issues (2011)
Volume 3: 4 Issues (2010)
Volume 2: 4 Issues (2009)
Volume 1: 4 Issues (2008)
View Complete Journal Contents Listing