Unsupervised Deep Keyphrase Generation

TL;DR

This paper introduces AutoKeyGen, an unsupervised deep learning approach for keyphrase generation that leverages a corpus-wide phrase bank and a generative model to predict both present and absent keyphrases without annotated data.

Contribution

AutoKeyGen is a novel unsupervised method that constructs a phrase bank and trains a deep generative model for keyphrase prediction without human annotations.

Findings

AutoKeyGen outperforms unsupervised baselines.

AutoKeyGen can surpass some supervised methods.

Effective in predicting absent keyphrases.

Abstract

Keyphrase generation aims to summarize long documents with a collection of salient phrases. Deep neural models have demonstrated a remarkable success in this task, capable of predicting keyphrases that are even absent from a document. However, such abstractiveness is acquired at the expense of a substantial amount of annotated data. In this paper, we present a novel method for keyphrase generation, AutoKeyGen, without the supervision of any human annotation. Motivated by the observation that an absent keyphrase in one document can appear in other places, in whole or in part, we first construct a phrase bank by pooling all phrases in a corpus. With this phrase bank, we then draw candidate absent keyphrases for each document through a partial matching process. To rank both types of candidates, we combine their lexical- and semantic-level similarities to the input document. Moreover, we utilize these top-ranked candidates as to train a deep generative model for more absent keyphrases. Extensive experiments demonstrate that AutoKeyGen outperforms all unsupervised baselines and can even beat strong supervised methods in certain cases.