KPDrop: Improving Absent Keyphrase Generation
This addresses a key bottleneck in keyphrase generation for document summarization, offering an incremental improvement over existing methods.
The paper tackles the challenge of generating absent keyphrases (phrases not in the document) by proposing KPDrop, a model-agnostic method that drops present keyphrases during training to create artificial absent ones, consistently improving performance in supervised and semi-supervised settings.
Keyphrase generation is the task of generating phrases (keyphrases) that summarize the main topics of a given document. Keyphrases can be either present or absent from the given document. While the extraction of present keyphrases has received much attention in the past, only recently a stronger focus has been placed on the generation of absent keyphrases. However, generating absent keyphrases is challenging; even the best methods show only a modest degree of success. In this paper, we propose a model-agnostic approach called keyphrase dropout (or KPDrop) to improve absent keyphrase generation. In this approach, we randomly drop present keyphrases from the document and turn them into artificial absent keyphrases during training. We test our approach extensively and show that it consistently improves the absent performance of strong baselines in both supervised and resource-constrained semi-supervised settings.