A Tree-based Indexing Approach for Diverse Textual Similarity Search

Textual information is ubiquitous in our lives and is becoming an important component of our cognitive society. In the age of big data, we consistently need to traverse substantial amounts of data even to find a little information. To quickly acquire effective information, it is necessary to implement a textual similarity search based on an appropriate index structure to efficiently find results. In this article, we study top-k textual similarity search and develop a tree-based indexing approach that can construct indices to support various similarity functions. Our indexing approach clusters similar records in the same branch offline to improve the performance of online search. Based on the index tree, we present a top-k search algorithm with efficient pruning techniques. The experimental results demonstrate that our algorithm can achieve higher performance and better scalability than the baseline method.