SenSeNet: Neural Keyphrase Generation with Document Structure
This work provides an incremental improvement for researchers working on keyphrase generation by better leveraging document structure.
This paper addresses the problem of keyphrase generation (KG) by incorporating document structure, which previous methods ignored. The proposed Sentence Selective Network (SenSeNet) uses a straight-through estimator and weak supervision to select important sentences, consistently improving the performance of major seq2seq-based KG models.
Keyphrase Generation (KG) is the task of generating central topics from a given document or literary work, which captures the crucial information necessary to understand the content. Documents such as scientific literature contain rich meta-sentence information, which represents the logical-semantic structure of the documents. However, previous approaches ignore the constraints of document logical structure, and hence they mistakenly generate keyphrases from unimportant sentences. To address this problem, we propose a new method called Sentence Selective Network (SenSeNet) to incorporate the meta-sentence inductive bias into KG. In SenSeNet, we use a straight-through estimator for end-to-end training and incorporate weak supervision in the training of the sentence selection module. Experimental results show that SenSeNet can consistently improve the performance of major KG models based on seq2seq framework, which demonstrate the effectiveness of capturing structural information and distinguishing the significance of sentences in KG task.