Lalita Narupiyakul

A Rule-Based Approach for Availability of Web Service

Sustainable success of service oriented applications relies on capabilities to manage possible service failures. To substitute a failed service with some other equivalent service is unavoidable in recovering a suspended application due to failure of a constituent service. In this paper, we report a rule based approach to Web service substitution in order to secure availability of services. Availability provides delivery assurance for each Web service so that Simple Object Access Protocol (SOAP) messages cannot be lost undetectably, especially in a Web service composition. The rules are written in Semantic Web Rule Language. The rules are a formal representation of a categorization-based scheme to identify exchangeable Web services. This scheme not only tackles the issue of heterogeneity of domain ontology in describing the Web services, it also adapts itself by learning newly discovered ontology instances. A technical framework of Web service substitution using rule based deduction is demonstrated. Experiments on service substitution based on the proposed framework achieve a best precision of 85%.

A stochastic knowledge-based Thai text-to-speech system

We describe the development of our Thai text-to-speech (TTS) system. Thai TTS system transforms Thai texts to the sequence of appropriate sounds for Thai speech. Thai complexity requires approximately four hundred rules including main and specific rules to derive most pronunciations for our rule-based approach grounded on Thai syllable structure analysis. An exception dictionary that covers anomalous pronunciations and a rule inference engine that determines sentence structures are included to improve the quality of Thai TTS. Speech generation by concatenative synthesis is a sequential step that transforms sound symbols to synthetic speech. We have tested our system with magazine and internet articles, together with articles from the experiments of other researchers and we report the results of this informal evaluation. Most syllables from Thai written strings can be converted to phonetic symbols. With a compact Thai unit inventory, the concatenative synthesis system can synthesize synthetic speech covering many Thai syllables.

Thai syllable-based Information Extraction using Hidden Markov Models

Information Extraction (IE) is a method which analyzes the information and retrieves significant segments or fields for insertion into tables or databases by automatic extraction. In this paper, we employ a statistical model for an IE system. Thai syllable-based information extraction using Hidden Markov Models (HMM) is our proposed method for automated information extraction. In our system, we develop a non-dictionary based method which requires a rule-based system for syllable segmentation. We employ a Viterbi algorithm, which is a statistical system for learning/testing our corpus, and extract the required fields from the information in corpus.

Enhancing E-Service Collaboration with Enforcement and Relationship Management: A Methodology from Requirements to Event Driven Realization

In a business-to-business B2B e-service environment, cross-organizational collaboration is important for attaining the interoperability of business processes and their proper enactment. The authors find that B2B collaboration can be divided into multiple layers and perspectives, which has not been adequately addressed in the literature. Besides regular e-service process enactment, robust collaboration requires enforcement, while quality collaboration involves relationship management. These problems are challenging, as they require the enactment of business processes and their monitoring in counter parties outside an organizations boundary. This paper presents a framework for B2B process collaboration with three layers, namely, collaboration requirements layer, business rule layer, and system implementation layer. The collaboration requirements layer specifies the cross-organizational requirements of e-service processes. In the business rule layer, detailed knowledge of these three types of process collaboration requirements is defined as business rules in a unified Event-Condition-Action ECA form. In the system implementation layer, event collaboration interfaces are supported by contemporary Enterprise JavaBeans and Web Services. Based on this architecture, a methodology is presented for the engineering of e-service process collaboration from high-level business requirements down to system implementation details. As a result, B2B process collaboration can be seamlessly defined, enacted, and enforced. Conceptual models of various layers are given in the Unified Modeling Language UML. We illustrate the applicability of our framework with a running example based on a supply-chain process and evaluate our approach from the perspective of three main stakeholders of e-collaboration, namely users, management, and systems developers.

Focus to emphasize tone analysis for prosodic generation

Emphasizing prosody of a sentence at its focus part when producing a speakers utterance can improve the recognition rate to hearers and reduce its ambiguity. Our objective is to address this challenge by analysing the concept of foci in speech utterances and the relationship of focus, speakers intention and prosody. Our investigation is aimed at understanding and modelling how a speakers utterances are influenced by the speakers intentions. The relationship between speakers intentions and focus information is used to consider which parts of the sentence serve as the focus parts. We propose using the Focus to Emphasize Tone (FET) analysis, which includes: (i) generating the constraints for foci, speakers intention and prosodic features, (ii) defining the intonation patterns, (iii) labelling a set of prosodic marks for a sentence. We also design the FET structure to support our analysis and to contain focus, speakers intention and prosodic components. An implementation of the system is described and the evaluation results on the CMU Communicator (CMU-COM) dataset are presented.

Focus to Emphasize Tone Structures for Prosodic Analysis in Spoken Language Generation

We analyze the concept of focus in speech and the relationship between focus and speech acts for prosodic generation. We determine how the speakers utterances are influenced by speakers intention. The relationship between speech acts and focus information is used to define which parts of the sentence serve as the focus parts. We propose the Focus to Emphasize Tones (FET) structure to analyze the focus components. We also design the FET grammar to analyze the intonation patterns and produce tone marks as a result of our analysis. We present a proof-of-the-concept working example to validate our proposal. More comprehensive evaluations are part of our current work.