Intelligent summarization of web documents
To relieve the pain caused by information overload, many researches have been carried out to provide high-quality summarizations so that the user can quickly locate the desired information. Intelligent Summarizer (I-Summarizer) is a system which can present desired sizes of summary that consists of...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Language: | English |
| Published: |
2009
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/17900 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | To relieve the pain caused by information overload, many researches have been carried out to provide high-quality summarizations so that the user can quickly locate the desired information. Intelligent Summarizer (I-Summarizer) is a system which can present desired sizes of summary that consists of important sentences originated from the multiple web documents. In this report, I-Summarizer is modified by replacing its original Fuzzy Co-clustering algorithm with Non-negative Matrix Tri-factorization (Tri-NMF) clustering algorithm. The purpose is to develop a new summarization system with a different clustering algorithm so that to investigate the performances of different systems. The report discusses the complete processes of modifying I-Summarizer from implementing Tri-NMF to integration with I-Summarizer, subsequently provides the evaluation of summarized outputs. The report concludes with the objectives achieved by developing the new summarization system based on I-Summarizer, along with the recommendations for future development. |
|---|