Keyphrase Generation: A Multi-Aspect Survey

TL;DR

This survey reviews the evolution of keyphrase generation methods, emphasizing recent neural network-based abstractive approaches that produce meaningful keyphrases and achieve state-of-the-art results.

Contribution

It provides a comprehensive overview of extractive and abstractive keyphrase generation techniques, focusing on neural network advancements and releasing a large dataset for research.

Findings

Neural network-based abstractive methods outperform traditional extractive approaches.

A large dataset of scientific articles and keyphrases has been created and shared.

Keyphrase generation research has evolved significantly over the last two decades.

Abstract

Extractive keyphrase generation research has been around since the nineties, but the more advanced abstractive approach based on the encoder-decoder framework and sequence-to-sequence learning has been explored only recently. In fact, more than a dozen of abstractive methods have been proposed in the last three years, producing meaningful keyphrases and achieving state-of-the-art scores. In this survey, we examine various aspects of the extractive keyphrase generation methods and focus mostly on the more recent abstractive methods that are based on neural networks. We pay particular attention to the mechanisms that have driven the perfection of the later. A huge collection of scientific article metadata and the corresponding keyphrases is created and released for the research community. We also present various keyphrase generation and text summarization research patterns and trends of the last two decades.