Semantic Web Search Through Natural Language Dialogues

Semantic Web Search Through Natural Language Dialogues

Dora Melo (Coimbra Business School, Portugal & Laboratory of Informatics, Systems and Parallelism (LISP), Portugal), Irene Pimenta Rodrigues (University of Évora, Portugal & Laboratory of Informatics, Systems and Parallelism (LISP), Portugal) and Vitor Beires Nogueira (University of Évora, Portugal & Laboratory of Informatics, Systems and Parallelism (LISP), Portugal)
Copyright: © 2018 |Pages: 21
DOI: 10.4018/978-1-5225-5042-6.ch012
OnDemand PDF Download:
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

The Semantic Web as a knowledge base gives to the Question Answering systems the capabilities needed to go well beyond the usual word matching in the documents and find a more accurate answer, without needing the user intervention to interpret the documents returned. In this chapter, the authors introduce a Dialogue Manager that, throughout the analysis of the question and the type of expected answer, provides accurate answers to the questions posed in Natural Language. The Dialogue Manager not only represents the semantics of the questions but also represents the structure of the discourse, including the user intentions and the questions' context, adding the ability to deal with multiple answers and providing justified answers. The system performance is evaluated by comparing with similar question answering systems. Although the test suite is of small dimension, the results obtained are very promising.
Chapter Preview
Top

Cooperative QA systems are automatic systems of question and answer that automatically collaborate with the users, in order to obtain the information and clarification needed to provide the correct answer. These systems provide the user with additional information, intermediate answers, qualified answers and/or alternative questions. An approach for processing cooperatives answers over databases is presented in Minker (1998). In McGuinness (2004), the author presents a set of techniques that promote the enhancement, its potential and impact on QA systems. Farah Benamara presents several works in this area: in Benamara (2004b), presents a logic-based model for accurate generation of intentional answers using a Cooperative QA system; in Benamara (2004a), presents a proposal for construction of a Logic-Based QA system, WEBCOOP, that integrates knowledge representation and advanced strategies of reasoning to generate cooperative answers to web queries. More recently, in Bakhtyar, Dang, Inoue, and Wiese (2014), the authors present an implementation of conceptual inductive learning operators in a prototype system for cooperative query answering, which can also be used as a usual concept learning mechanism for concepts described in first-order predicate logic.

Complete Chapter List

Search this Book:
Reset