Exclusive hierarchical decoding for deep keyphrase generation
Abstract
Keyphrase generation (KG) aims to summarize the main ideas of a document into a set of keyphrases.A new setting is recently introduced into this problem, in which, given a document, the model needs to predict a set of keyphrases and simultaneously determine the appropriate number of keyphrases to produce.Previous work in this setting employs a sequential decoding process to generate keyphrases.However, such a decoding method ignores the intrinsic hierarchical compositionality existing in the keyphrase set of a document.Moreover, previous work tends to generate duplicated keyphrases, which wastes time and computing resources.To overcome these limitations, we propose an exclusive hierarchical decoding framework that includes a hierarchical decoding process and either a soft or a hard exclusion mechanism.The hierarchical decoding process is to explicitly model the hierarchical compositionality of a keyphrase set.Both the soft and the hard exclusion mechanisms keep track of previouslypredicted keyphrases within a window size to enhance the diversity of the generated keyphrases.Extensive experiments on multiple KG benchmark datasets demonstrate the effectiveness of our method to generate less duplicated and more accurate keyphrases 1 .
Authors: Wang Chen, Hou Pong Chan, Piji Li, Irwin King
Published in: Annual Meeting of the Association for Computational Linguistics (ACL) (2020)