Showing papers by "Zuhair Bandar published in 2009"

A semantic-based conversational agent framework

Abstract: This paper focuses on the implementation of a novel semantic-based Conversational Agent (CA) framework. Traditional CA frameworks interpret scripts consisting of structural patterns of sentences. User input is matched against such patterns and an associated response is sent as output. This technique, which takes into account solely surface information, that is, the structural form of a sentence, requires the scripter to anticipate the inordinate ways that a user may send input. This is a tiresome and time-consuming process. As such, a semantic-based CA that interprets scripts consisting of natural language sentences will alleviate such burden. Using a pre-determined, domain-specific scenario, the CA was evaluated by participants indicating promising results.

Towards a New Generation of Conversational Agents Based on Sentence Similarity

Abstract: The Conversational Agent (CA) is a computer program that can engage in conversation using natural language dialogue with a human participant. Most CAs employ a pattern-matching technique to map user input onto structural patterns of sentences. However, every combination of utterances that a user may send as input must be taken into account when constructing such a script. This chapter was concerned with constructing a novel CA using sentence similarity measures. Examining word meaning rather than structural patterns of sentences meant that scripting was reduced to a couple of natural language sentences per rule as opposed to potentially 100s of patterns. Furthermore, initial results indicate good sentence similarity matching with 13 out of 18 domain-specific user utterances as opposed to that of the traditional pattern matching approach.

Fuzzification of discrete attributes from financial data in fuzzy classification trees

Abstract: Fuzzy Decision Trees have been successfully applied to both classification and regression problems by allowing gradual transitions to exist between attribute values. Methodologies for fuzzification in fuzzy trees currently create such gradual transitions for continuous attributes. This is achieved by automatically creating fuzzy regions around tree nodes using an optimization algorithm or by using the knowledge of a human expert to create a series of fuzzy sets which are representative of the attributes domain. A problem occurs when trying to construct a fuzzy tree from real world data which comprises of only discrete or a mixture of discrete and continuous attributes. Discrete attribute values have no proximity to other values in the decision space, as there is no continuum between values. Consequently, within a fuzzy tree they are interpreted as crisp sets and contribute little towards the final outcome. This paper proposes a new approach for the fuzzification of discrete attributes in fuzzy decision trees. The approach ranks discrete values on the basis of their effect on the outcome rate and assigns a possibility of being a specific outcome. Experiments carried out on two real world financial datasets which contain a significant proportion of discrete attributes show improved classification accuracy compared with a crisp interpretation of such attributes within fuzzy trees.

Elgasir: An algorithm for creating fuzzy regression trees

Abstract: This paper presents a new fuzzy regression tree algorithm known as Elgasir, which is based on the CHAID regression tree algorithm and Takagi-Sugeno fuzzy inference. The Elgasir algorithm is applied to crisp regression trees to produce fuzzy regression trees in order to soften sharp decision boundaries inherited in crisp trees. Elgasir generates a fuzzy rule base by applying fuzzy techniques to crisp regression trees using Trapezoidal membership functions. Then Takagi-Sugeno fuzzy inference is used to aggregate the final output from the fuzzy implications. The approach is evaluated using two problem sets from the UCI repository. Experiments conducted yield an improvement in the performance of fuzzy regression trees compared with crisp CHAID trees. The generated fuzzy regression trees are more robust and presented in a highly visual format which is easy to understand.