An Integrated Approach for Keyphrase Generation via Exploring the Power of Retrieval and Extraction

TL;DR

This paper introduces an integrated keyphrase generation method combining extractive, generative, and retrieval techniques within a multi-task learning framework, significantly improving performance over existing methods.

Contribution

The novel multi-task framework jointly trains extractive and generative models, incorporating retrieval-based external knowledge and a neural merging module for enhanced keyphrase generation.

Findings

Outperforms state-of-the-art methods on five benchmarks

Effectively combines extraction, generation, and retrieval for better results

Improves keyphrase relevance and diversity

Abstract

In this paper, we present a novel integrated approach for keyphrase generation (KG). Unlike previous works which are purely extractive or generative, we first propose a new multi-task learning framework that jointly learns an extractive model and a generative model. Besides extracting keyphrases, the output of the extractive model is also employed to rectify the copy probability distribution of the generative model, such that the generative model can better identify important contents from the given document. Moreover, we retrieve similar documents with the given document from training data and use their associated keyphrases as external knowledge for the generative model to produce more accurate keyphrases. For further exploiting the power of extraction and retrieval, we propose a neural-based merging module to combine and re-rank the predicted keyphrases from the enhanced generative model, the extractive model, and the retrieved keyphrases. Experiments on the five KG benchmarks demonstrate that our integrated approach outperforms the state-of-the-art methods.