Research Area:  Machine Learning

Abstract:

In this paper, we study automatic keyphrase generation. Although conventional approaches to this task show promising results, they neglect correlation among keyphrases, resulting in duplication and coverage issues. To solve these problems, we propose a new sequence-to-sequence architecture for keyphrase generation named CorrRNN, which captures correlation among multiple keyphrases in two ways. First, we employ a coverage vector to indicate whether the word in the source document has been summarized by previous phrases to improve the coverage for keyphrases. Second, preceding phrases are taken into account to eliminate duplicate phrases and improve result coherence. Experiment results show that our model significantly outperforms the state-of-the-art method on benchmark datasets in terms of both accuracy and diversity.

Keywords:  
Keyphrase Generation
Correlation Constraints
RNN
Machine Learning
Deep Learning

Author(s) Name:  Jun Chen, Xiaoming Zhang, Yu Wu, Zhao Yan, Zhoujun Li

Publisher name:  arXiv:1808.07185

DOI:  10.48550/arXiv.1808.07185

Volume Information:  

Paper Link:   https://arxiv.org/abs/1808.07185