本文利用事件相关文档的特点，提出了基于多特征的句子聚类方法，以期获得事件的各个侧面信息。
According to the characteristics of the related texts, this paper presents a sentence clustering method based on multi-features for getting profile information of the event.
在事件相关文档的检索中，事件主题的迁移和分化与相似事件的干扰是影响系统性能的两个主要因素。
It is differentiation and transference of the event topic and interference from other similar event that restrict ability of retrieval system in retrieval of event relevant documents.
第二、以用户阅读的少量文档为查询依据进行事件相关文档的收集，提出了一种基于事件框架知识的事件相关文档的检索方法。
The second, present a retrieval method of event-relevant documents based on event frame knowledge according to several documents read by users.
应用推荐