Cross-Language Information Retrieval Systems which is using dictionary-based method / Wong Jung Bill
This dissertation proposes a Malay-English cross-language information retrieval systems which is using dictionary-based method. This system first translates a given Malay query into English query using a Malay-English dictionary, and then retrieve document relevant to the translated English query. T...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
2005
|
| Subjects: | |
| Online Access: | http://studentsrepo.um.edu.my/11054/1/Wong_Jun_Bill_(Cross_Language_Information).pdf http://studentsrepo.um.edu.my/11054/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Universiti Malaya |
| Summary: | This dissertation proposes a Malay-English cross-language information retrieval systems which is using dictionary-based method. This system first translates a given Malay query into English query using a Malay-English dictionary, and then retrieve document relevant to the translated English query. This CLIR system will be a useful system that allows users who want to use both Malay and English natural language query to retrieve English documents. Dictionary-based CLIR problems are discussed in this proposal and some methods have been proposed in order to address the problems. The methods are including query identification, n-gram handling, dictionary translation, abbreviation cheecking and query structuring. In query translation, to drive possible translation for user query, dictionary is used and a transliteration method is performed, which generates translation for untranslatable Malay words based on-ngram based matching. This solution will improve the query translation accuracy. This system will be developed on Windows 2000 Professional and the software development tools that will be utilized are Apache web server, PHP, Internet Explorer, and will also incorporate with the My SQL Server as the database management system. |
|---|