Could Dr. Rizal PhD be possible?

Research Proposal
Research Field: EXPERT SYSTEMS
Research Title: Natural Language Processing(NLP) For Speech Input/Output In A Computer Expert System

1. Background
   
   The development of Artificial Intelligence has spawn many applications from creating artificial neural network for Self-learning Systems to case reasoning systems for Expert Systems. Experts Systems are mostly used today to gain answers to myriads of knowledge, however, the problem lies in recognizing inputs, searching the right data to be processed and outputting the data in an understandable form. Previous work that have been done with Natural Language speech input/output are mostly restricted to English. A problem lies for countries that use mixed languages like Malaysia, where English and Malay are often used interchangeably.
   
   This leaves an opportunity to create a whole set of Media Library to recognized English, Malay and derivatives of the two languages for natural language processing. A trained Expert System can therefore use the much more relaxed natural language set for input and output that can recognized crude English grammar with mixed of Malay and English. Consequently, producing a better, robust and practical use of an expert system.

2. Previous Work Done on NLP
   A popular work in Natural Language Processing(NLP) is GATE (General Architecture for Text Engineering), it aims to provide a software infrastructure for researchers and developers working in NLP. GATE has now been widely available for four years. Using GATE will eliminate the hassle to:

• store data on disk
• display data
• load processor modules and data stores into processes
• initiate and administer processes
• divide computation between client and server
• pass data between processes and machines.

This research will evaluate GATE potential and feasibility to be used as an NLP library to be integrated into an Expert System. It will also involve research work to use NLP for languages other than English, primarily the use of Malay language and the combination of English and Malay Language.
GATE has been used in many projects for language processing and data extraction. It has also been used for building NLP systems that can recognized German language. The challenging mark for this research is making GATE to work with both Malay language and English language.

3. AIML for Expert Systems
   
   The Expert System to be used in this research will use the power of AIML. AIML, or Artificial Intelligence Mark-up Language enables people to input knowledge into chat-bots based on the A.L.I.C.E free software technology. AIML was developed by the Alicebot free software community and Dr. Richard S. Wallace. It was originally adapted from a non-XML grammar also called AIML, and formed the basis for the first Alicebot, A.L.I.C.E., the Artificial Linguistic Internet Computer Entity.
   
   AIML, describes a class of data objects called AIML objects and partially describes the behavior of computer programs that process them. AIML objects are made up of units called topics and categories, which contain either parsed or unparsed data.
   
   Parsed data is made up of characters, some of which form character data, and some of which form AIML elements. AIML elements encapsulate the stimulus-response knowledge contained in the document. Character data within these elements is sometimes parsed by an AIML interpreter, and sometimes left unparsed for later processing by a Responder.
   
   The research will involve the use of AIML with Program D as its engine. The core of the Expert System's responds to questions and answers will be processed through AIML coding. These coding must be able to recognized the complexity of using languages other than English, or a mix language of English and Malay. Several work has been done to create chatbots that are also experts systems. These are also done using AIML based from the original ALICE programmed used in previous work.

3. Previous work done on Experts Systems Integration with NLP
   
   A popular open source development in AI is Program D. It is the most widely used open source / free AIML interpreter in the world and can be used to create an Expert System. It is the most feature-complete implementation of the current AIML specification. It supports unlimited multiple bots in a single server instance, and has an open-ended architecture for interacting via any interface imaginable. (The standard release includes interfaces to instant messaging platforms, IRC, HTML forms, and Flash, and provides a working servlet implementation.) It includes an automated testing framework for testing your knowledge bases, and is packaged with an AIML Test Suite that verifies that the program itself complies to the AIML specification.
   
   Program D is known to work with many different languages / character sets. Its component-oriented architecture allows it to be integrated into any application framework desirable. It is implemented in Java, and uses many features of the latest JDK to provide optimum code reliability. It is actively maintained and supported.
   
   There are some work being done in Project D to support speech. The most integral part of this research, as proof of concept, is to make Project D work with GATE to process natural languages and create speech for input/output for an Expert System.

5. Objectives of Research
   
   The main objective of this paper is to present ideas for future researchers and developers to create Expert Systems that are more robust in recognizing languages other than English or a combination of languages. These are more practical implementation of NLP for experts systems.
   
   This paper will also describe a computer program which accepts and "understands" a comfortable, but relaxed set of two natural languages, English, Malay and derivatives of both languages. Certain difficulties are inherent in this problem of making a machine "understand" English, Malay or a combination of these two languages. Within the limited framework of the subject matter understood by the program, many of these problems are solved or circumvented. I shall describe these problems and my solutions, and point out those solutions which I feel have general applicability. I will also indicate which must be replaced by more general methods to be really useful, and give my ideas about what general solutions to these particular problems might entail.

6. Research Methodology
   
   The research methodology used in this research takes the following approach:

1. Domain Analysis
   1. Analysis of research descriptions
   2. Examples
   3. Abstracts
   4. Journals
   5. Papers.
2. General Architecture for System
   1. Comprehension of tools being used for research.
   2. Requirement Analysis
   3. Design and Implementation
   4. Explanation and Design of software
3. Demonstration and example of implementation
4. Empirical data testing and statistical overview
5. Contributions for research and benefits of research
6. Future Work

7. Significant Use For This Research Paper
   
   This paper will be useful to guide software developers and researchers to develop software that uses natural language processing for speech and Expert Systems. It will also help developers and researchers to create new support for different languages to be recognized and possibly integrated into an Expert System for the purpose of education and knowledge sharing.

8. Benefits Of This Research
   
   The benefits out of this research to society is the possibility to create a database of knowledge in a Expert System that has lower language barriers. This allows education softwares to be created for the community. In will also spawn new development and revamp how computers interact with human beings. It could possibly revolutionize how human beings interact with computers and enhance learning through computers. As for Malaysia, the use of this research can be the basis to create educational softwares, consumer relationships softwares, knowledge based softwares that can be used as experts systems in the form of robots, chatbots, touch screen displays and many more.

9. List of References
   ...////......exhaustive list of resources
   

10. Research Schedule
    

Phases	Description	Duration
Analysis of research descriptions	To analyze research domain and define scope of research.	1 month
Examples	Information Gathering for examples in the use of GATE and Program D	2 months
Journals	Information Gathering for journals of previous work being done.	1 month
Papers	Information Gathering for papers of previous work being done	1 month
Comprehension of tools being used for research.	Comprehension of tools, languages and integration methods for research in GATE, PROGRAM D and AIML language sets.	3 months
Requirement Analysis	Requirement analysis for software development, language sets and database	3 months
Design and Implementation	Design of overall system for proof of concept	3 months
Explanation and Design of software	Thorough write up for difficulties, limitations, and possible enhancements	2 months
Demonstration and example of implementation	System demonstration and prototype	1 month
Empirical data testing and statistical overview	Statistical data of performance, language recognition and success rate	3 months

11. Proposed Supervisor
    
    I intend to have Associate Professor Lawrence K. Saul from University of Pennsylvania as my supervisor for my PhD. research. Currently, Professor Saul is attached to the GRASP Laboratory, Department of Computer & Information Science, University of Pennsylvania. His experience in machine learning, pattern recognition, and voice processing could help me realize my research and possibly provide guidelines for my work.