Research of key-phrase extraction based on lexical chain

A novel algorithm for key-phrase extraction based on lexical chain is proposed in this paper. By constructing lexical chains for each article, the article's multiple depiction clews can be reflected, and some strong lexical chains with high quality can be extracted to represent main content of this article. After previous operations, key-phrases, which can fully express topic information of strong chain from different aspects, are extracted. Experiments demonstrate that key-phrases from this algorithm can cover article's topic more completely. This algorithm can remove redundancy that different key-phrases reflect same meanings, and can dynamically decide the size of output key-phrase set by distribution of topic information. This method outperforms the method which uses statistics to perform extraction.