AdaptiveUKE: Towards adaptive unsupervised keyphrase extraction with gated topic modeling

Qi Liu, Wenjun Ke, Xiaoguang Yuan, Yuting Yang, Hua Zhao, Peng Wang

Abstract: Highlights•Documents in real settings exhibit complex, diverse semantic richness.•Keyphrases from a document often distribute across multiple topics.•We propose a gated topic modeling schema for semantic-adaptive assignment.•Scoring candidates by topic importance significantly improves keyphrase diversity.