Unsupervised Deep Keyphrase Generation
This addresses the need for keyphrase generation in domains where labeled data is scarce, though it is incremental as it builds on existing deep learning approaches.
The paper tackles the problem of generating keyphrases for documents without requiring annotated data, by constructing a phrase bank and using partial matching to train a deep generative model. The result is that AutoKeyGen outperforms unsupervised baselines and can sometimes beat supervised methods.
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.