Skip navigation

An intelligent question: answering system for natural language

An intelligent question: answering system for natural language

Yamani, Ahmed A. S. (1998) An intelligent question: answering system for natural language. PhD thesis, University of Greenwich.

[img] PDF
Ahmed_Yamani_1998.pdf - Published Version
Restricted to Repository staff only until 16 March 2019.
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (124MB)

Abstract

As applications of information storage and retrieval systems are becoming more widespread, there is an increased need to be able to communicate with these systems in a natural way. Natural Language applications in the 1990s, as well as in the foreseeable future, have more demanding requirements. Current Natural Language Processing approaches alone have proven to be insufficient as they lack to obtain linguistic understanding. A more suitable approach would be to adopt Computational Linguistics theories, such as the Lexical-Functional Grammar (LFG) theory complemented with Artificial Intelligence representation and processing techniques.

A prototype Question-Answering System has been developed. It takes Natural Language parsed interrogatives, produces the Functional and Semantic structures according to the LFG representation. It compares the functional behaviour of verbs and their linguistic associations in a given query with a general Object Model in that specific domain. It will then attempt to deduce more information from the given processed text and represent it for possible queries. The structural rules of the LFG and the deduced common-sense domain specific information resolve most of the common ambiguities found in Natural Languages and enhance the understanding ability of the proposed prototype.

The LFG theory has been adopted and extended: (i) to examine the constituents of the theoretical, syntactic and semantic of Arabic interrogatives, an area which has not been
thoroughly investigated, (ii) to represent the Functional and Semantic Structures of the Arabic interrogatives, (iii) to overcome the word-order problem associated with some Natural languages such as Arabic, (iv) to add understanding capabilities by capturing the common-sense domain specific knowledge within a specific domain.

Item Type: Thesis (PhD)
Additional Information: uk.bl.ethos.241634
Uncontrolled Keywords: natural language, applications, information storage, information retrieval, computational linguistics, theory, lexical-functional grammar, LFG,
Subjects: P Language and Literature > P Philology. Linguistics
Q Science > Q Science (General)
Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Pre-2014 Departments: School of Computing & Mathematical Sciences
School of Computing & Mathematical Sciences > Centre for Numerical Modelling & Process Analysis > Computational Science & Engineering Group
Last Modified: 13 Mar 2018 16:12
Selected for GREAT 2016: None
Selected for GREAT 2017: None
Selected for GREAT 2018: None
URI: http://gala.gre.ac.uk/id/eprint/8253

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics