A Study on Efficient Searching Top-k Semantic Similar Sentences

摘要

Semantic similarity measure between sentences is an important issue in many applications, such as, text mining, Web page retrieval, dialogue systems, and so forth. Although it has been explored for several decades, most of these studies focus on how to improve the effectiveness of the problem. In this paper, we address the efficiency issue, i.e., for a given sentence collection, how to efficiently discover the top-k most semantic similar sentences to the query. It is a very important issue for real applications while existing state-of-the-art strategies cannot satisfy the performance requirement of the users. We introduce a general framework to tackle the issue, in which several efficient strategies are proposed. Extensive experimental evaluations demonstrate that our approach outperforms the state-of-the-art methods.