Automatic Chinese Summarization Method Based on the HowNet and Clustering Algorithm
| Autor: | Zongyao Ding, Dongmei Wang, Yi Zhu, Gang Bai |
|---|---|
| Rok vydání: | 2007 |
| Předmět: |
Computer science
business.industry Computer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing) Pattern recognition computer.software_genre Partition (database) Automatic summarization Word lists by frequency Feature (machine learning) Vector space model Data mining Artificial intelligence Paragraph Cluster analysis business computer Word (computer architecture) |
| Zdroj: | Proceedings on Intelligent Systems and Knowledge Engineering (ISKE2007). |
| DOI: | 10.2991/iske.2007.100 |
| Popis: | To solve the problems in traditional automatic Chinese summarization, a new method based on the word concept and clustering is presented in this paper. Different from the normal statistical method, concept is used as feature instead of word. Also, instead of word frequency statistics, word concept frequency statistics (WCFS) is used in our approach. For each paragraph, a conceptual vector space model is established, and then the clustering algorithm is used for multiple topic partition. The evaluation results show that the method proposed in this paper is more efficient and robust than the traditional one. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|