Study on core Technologies of Query-oriented Automatic Summarization

In the paper, how to meet the users' need plays a very important role in the study on the query-oriented automatic summarization. Combining with the influence of text granularities and query information, we construct a model to explain the relationship between text granularities, point out the way based on the semantic relation to test text similarity, adopt a strategy to sentence dynamically allocation to produce summarization. Experimental results show that there is less redundant but more comprehensive information in the summarization. It confirms that the model and the strategy are effective and feasible for faster query speed and better results. (C) 2011 Published by Elsevier Ltd. Selection and/or peer-review under responsibility of [CEIS 2011]