Dynamic Bayesian Networks and Variable Length Genetic Algorithm for Dialogue Act Recognition

Ali Yahya, Anwar (2007) Dynamic Bayesian Networks and Variable Length Genetic Algorithm for Dialogue Act Recognition. PhD thesis, Universiti Putra Malaysia.

[img] PDF
577Kb

Abstract

The recognition of dialogue act is a task of crucial importance for the processing of natural language in many applications such as dialogue system. However, it is one of the most challenging problems. The current dialogue act recognition models, namely cue-based models, are based on machine learning techniques, particularly statistical ones. Despite the success of the cue-based models, they still have serious drawbacks. Among them are, inadequate representation of dialogue context, intra-utterance and inter-utterances independencies assumptions, inaccurate estimation of the recognition accuracy and suboptimality of the lexical cues selection approaches. Motivating by these drawbacks, this research proposes a new model of dialogue act recognition in which dynamic Bayesian machine learning is applied to induce dynamic Bayesian networks models from task-oriented dialogue corpus using sets of lexical cues selected automatically by means of new variable length genetic algorithm. In achieving this, the research is planned in three main stages. In the initial stage, the dynamic Bayesian networks models are constructed based on a set of lexical cues selected tentatively from the dialogue corpus. The results are compared with the results of static Bayesian networks and naïve bayes. The results confirm the merits of using dynamic Bayesian networks for dialogue act recognition. In the second stage, the previous ranking approaches are investigated for the selection of lexical cues. The main drawbacks of these approaches are highlighted, and based on that an alternative approach is proposed. The proposed approach consists of preparation phase and selection phase. The preparation phase transforms the original dialogue corpus into phrases space. In the selection phase, a new variable length genetic algorithm is applied to select the lexical cues. The results of the proposed approach are compared with the results of the ranking approaches. The results provide experimental evidences on the ability of the proposed approach to avoid the drawbacks of the ranking approaches. In the final stage; the dynamic Bayesian networks models are redesigned using the lexical cues generated from the proposed lexical cues selection approaches. The results confirm the effectiveness of proposed approaches for the design of dialogue act recognition model.

Item Type:Thesis (PhD)
Subject:Machine learning.
Subject:Genetic algorithms.
Chairman Supervisor:Associate Professor Ramlan Mahmod, PhD
Call Number:FSKTM 2007 17
Faculty or Institute:Faculty of Computer Science and Information Technology
ID Code:5217
Deposited By: Rosmieza Mat Jusoh
Deposited On:07 Apr 2010 02:58
Last Modified:27 May 2013 07:21

Repository Staff Only: Edit item detail

Document Download Statistics

This item has been downloaded for since 07 Apr 2010 02:58.

View statistics for "Dynamic Bayesian Networks and Variable Length Genetic Algorithm for Dialogue Act Recognition "


Universiti Putra Malaysia Institutional Repository

Universiti Putra Malaysia Institutional Repository is an on-line digital archive that serves as a central collection and storage of scientific information and research at the Universiti Putra Malaysia.

Currently, the collections deposited in the IR consists of Master and PhD theses, Master and PhD Project Report, Journal Articles, Journal Bulletins, Conference Papers, UPM News, Newspaper Cuttings, Patents and Inaugural Lectures.

As the policy of the university does not permit users to view thesis in full text, access is only given to the first 24 pages only.