Word Similarity Based on an Ensemble Model Using Ranking SVMs
WI-IAT '08 Proceedings of the 2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Volume 03
Hi-index | 0.00 |
Question answering system can provides a precise and concise answer to a natural language query. Question classification is very important for question answering, and the result of question classification affects the quality of question answering system directly. This paper presents a combination method for question classification based on pattern and semantic resource. We choose the interrogative words, question focus words and their first sememes as classification feature to realize fast question classification. Experimental results demonstrate the effectiveness of our method which attains the expected effects.