DKPE: Deep KeyPhrase Expansion

Abstract

Keyphrase provides accurate information of document content that is highly compact, concise, full of meanings, and widely used for discourse comprehension, organization, and text retrieval. Though previous studies have made substantial efforts for automated keyphrase extraction and generation, surprisingly, few studies have been made for KeyPhrase Expansion. This task aims to add more keyphrases for documents (e.g. scientific publications) via taking advantage of document content along with a very limited number of known keyphrases, which can widely be used to improve the keyphrases-involved NLP tasks. In this paper, we introduce a novel problem concerning KeyPhrase Expansion and propose a novel keyphrase expansion method with an encoder–decoder framework. We name it Deep KeyPhrase Expansion (DKPE) since it attempts to capture the deep semantic meaning of the document content together with known keyphrases via a deep learning framework. Specifically, the encoder and the decoder in DKPE play different roles to make full use of the known keyphrases. The former considers the keyphrase-guiding factors, which aggregates information of known keyphrases into context. On the contrary, the latter considers the keyphrase-inhibited factor to inhibit semantically repeated keyphrase generation. Extensive experiments on benchmark datasets demonstrate the efficacy of our proposed model.