Skip navigation
Run Run Shaw Library City University of Hong KongRun Run Shaw Library

Please use this identifier to cite or link to this item: http://dspace.cityu.edu.hk/handle/2031/4821
Title: NLP-based artificially intelligent chat-bot
Authors: Peswani, Sundeep Baldev
Department: Department of Electronic Engineering
Issue Date: 2007
Supervisor: Supervisor: Dr. Tsang, Peter W M.; Assessor: Dr. Wong, K W
Subjects: Natural language processing (Computer science)
Artificial intelligence.
Description: Nominated as OAPS (Outstanding Academic Papers by Students) paper by Department in 2007-08.
Abstract: Tools such as search engines and personal agents lack personality, evidenced by their mechanical acceptance of input and production of output, and practicality, demonstrated by their in-take of a single type of input, like keywords. To assuage these issues, techniques developed in Natural Language Processing (NLP) are used to produce a model of a system which combines a normal chatter-bot with a more intelligent document categorization and retrieval system, thereby creating a new digital assistant system. The NLP techniques used in this project include topic modeling, recursive distributed representation, which is a form of connectionist modeling, and Weizenbaum's ELIZA. The first of the three is used to categorize a corpus of documents, while the other techniques are used to interact with the user. Reliance on keywords was found to be unavoidable, but modeling the corpus to topics rather than a spatial distribution, such as that of frequency, proved to be successful at retrieving the relevant documents, to a certain extent. The topic modeling mechanism appeared to be highly influenced by the number of words in each document. The connectionist modeling was worse than ELIZA at recognizing trained phrases, but was better at dealing with unknown words.
Appears in Collections:Electrical Engineering - Undergraduate Final Year Projects 
OAPS - Dept. of Electrical Engineering 

Files in This Item:
File SizeFormat 
fulltext.html132 BHTMLView/Open
Show full item record


Items in Digital CityU Collections are protected by copyright, with all rights reserved, unless otherwise indicated.

Send feedback to Library Systems
Privacy Policy | Copyright | Disclaimer