Exploration on Efficient Similar Sentences Extraction

摘要

Semantic similarity measure between sentences is an essential issue for many applications, such as natural language processing, Web page retrieval, question-answer model, and so forth. Although there are a few studies exploring on this issue, most of them 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 semantic similar sentences to a query. The issue is very important for real applications because the data becomes huge and the existing state-of-the-art strategies cannot satisfy the users' performance requirement. We propose efficient strategies to tackle such problem based on a general framework. Extensive experimental evaluations conducted on two real datasets demonstrate that the efficiency of our proposal outperforms the state-of-the-art approach.