MIKE: Keyphrase Extraction by Integrating Multidimensional Information

MIKE: Keyphrase Extraction by Integrating Multidimensional Information
Title:
MIKE: Keyphrase Extraction by Integrating Multidimensional Information
Other Titles:
Conference on Information and Knowledge Management
Keywords:
Publication Date:
06 November 2017
Citation:
Abstract:
Traditional supervised keyphrase extraction models depend on the features of labelled keyphrases while prevailing unsupervised models mainly rely on structure of the word graph, with candidate words as nodes and edges capturing the co-occurrence information between words. However, systematically integrating all these multidimensional heterogeneous information into a unified model is relatively unexplored. In this paper, we focus on how to effectively exploit multidimensional information to improve the keyphrase extraction performance (MIKE). Specifically, we propose a random-walk parametric model, MIKE, that learns the latent representation for a candidate keyphrase that captures the mutual influences among all information, and simultaneously optimizes the parameters and ranking scores of candidates in the word graph. We use the gradient-descent algorithm to optimize our model and show the comprehensive experiments with two publicly-available WWW and KDD datasets in Computer Science. Experimental results demonstrate that our approach significantly outperforms the state-of-the-art graph-based keyphrase extraction approaches.
License type:
PublisherCopyrights
Funding Info:
Description:
ISBN:
978-1-4503-4918-5/17/11
Files uploaded:

File Size Format Action
fp0909-zhanga-2.pdf 834.49 KB PDF Open