Copyright © 2003 Elsevier Ltd. All rights reserved.
Ontology-based fuzzy event extraction agent for Chinese e-news summarization
Available online 1 May 2003.
Abstract
An Ontology-based Fuzzy Event Extraction (OFEE) agent for Chinese e-news summarization is proposed in this article. The OFEE agent contains Retrieval Agent (RA), Document Processing Agent (DPA) and Fuzzy Inference Agent (FIA) to perform the event extraction for Chinese e-news summarization. First, RA automatically retrieves Internet e-news periodically, stores them into the e-news repository, and sends them to DPA for document processing. Then, the DPA will utilize the Chinese Part-of-speech (POS) tagger provided by Chinese knowledge information processing group to process the retrieved e-news and filter the Chinese term set by Chinese term filter. Next, the FIA and Event Ontology Filter (EOF) extract the e-news event ontology based on the Chinese term set and domain ontology. Finally, the Summarization Agent (SA) will summarize the e-news by the extracted-event ontology. By the simulation, the proposed method can summarize the Chinese weather e-news effectively.
Author Keywords: Ontology; Fuzzy inference; Event extraction; Chinese e-news summarization; Natural language processing
Article Outline
- 1. Introduction
- 2. Ontology-based fuzzy event extraction agent
- 2.1. Object-oriented structure of domain ontology
- 2.2. The structure of e-news ontology
- 2.3. The architecture of OFEE agent
- 2.4. Retrieval agent and document processing agent
- 3. Fuzzy inference agent for event ontology extraction
- 3.1. The architecture of fuzzy inference agent
- 3.1.1. Layer 1 (input layer)
- 3.1.2. Layer 2 (input linguistic layer)
- 3.1.3. Layer 3 (rule layer)
- 3.1.4. Layer 4 (output linguistic layer)
- 3.1.5. Layer 5 (output layer)
- 3.2. Event ontology filter
- 4. Summarization agent for Chinese e-News summary
- 5. Conclusions
- Acknowledgements
- References






E-mail Article
Add to my Quick Links

Cited By in Scopus (21)

10), such as pore waters from reduced environments, the method was invalid. Despite this limitation, the flow injection analysis with OPA appeared to be a promising procedure for primary amine study as very good sensitivity (<0.1 μM) and reproducibility (relative standard deviation <10% at the 0.2–1 μM level) were obtained from analyses which took only 1 min per sample.





