Logo image
Hyperbolic Deep Keyphrase Generation
Conference proceeding   Peer reviewed

Hyperbolic Deep Keyphrase Generation

Yuxiang Zhang, Tianyu Yang, Tao Jiang, Xiaoli Li and Suge Wang
MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2022, PT II, Vol.13714, pp.521-536
Lecture Notes in Artificial Intelligence
01/01/2023

Abstract

Computer Science Computer Science, Artificial Intelligence Computer Science, Interdisciplinary Applications Computer Science, Theory & Methods Science & Technology Technology
Keyphrases can concisely describe the high-level topics discussed in a document, and thus keyphrase prediction compresses document's hierarchical semantic information into a few important representative phrases. Numerous methods have been proposed to use the encoder-decoder framework in Euclidean space to generate keyphrases. However, their ability to capture the hierarchical structures is limited by the nature of Euclidean space. To this end, we propose a new research direction that aims to encode the hierarchical semantic information of a document into the low-dimensional representation and then decompress it to generate keyphrases in a hyperbolic space, which can effectively capture the underlying semantic hierarchical structures. In addition, we propose a novel hyperbolic attention mechanism to selectively focus on the high-level phrases in hierarchical semantics. To the best of our knowledge, this is the first study to explore a hyperbolic network for keyphrase generation. The experimental results illustrate that our method outperforms fifteen state-of-the-art methods across five datasets.

Metrics

1 Record Views

Details

Logo image