Keyphrase Ranking Based on Second Order Co-Occurrence Analysis

State-of-the-art researches in unsupervised automatic keyphrase extraction focused on graph analysis. Keyphrase ranking is critical step in graph-based approaches. In this paper, we follow two main purposes including choice of good candidate phrases and computing importance of candidate phrase by considering the mutual information between words. Our documents representation improves the process of candidate phrases selection by constructing a single graph for all documents in the collection. We enjoy from parallel minimum spanning tree to prune irrelevant edge relations. We also consider second order co-occurrence of words by point-wise mutual information as a similarity measure and importance of terms to increase the performance of keyphrase ranking. We formed a single graph of cooccurrence network for all documents in the collection and analyze co-occurrence network with different settings. We compare our method with three baseline approaches of keyphrase extraction. Experimental results show that applying second order co-occurrence analysis improves keyphrases identification accuracy.

Keywords:

graph analysis , similarity measure , point-wise mutual information , co-occurrence networks , keyphrase ranking