Enhancing Keyphrase Generation by BART Finetuning with Splitting and Shuffling

Keyphrase generation is a task of identifying a set of phrases that best represent the main topics or themes of a given text. Keyphrases are dividend int present and absent keyphrases. Recent approaches utilizing sequence-to-sequence models show effectiveness on absent keyphrase generation. However, the performance is still limited due to the hardness of finding absent keyphrases. In this paper, we propose Keyphrase-Focused BART, which exploits the differences between present and absent keyphrase generations, and performs finetuning of two separate BART models for present and absent keyphrases. We further show effective approaches of shuffling keyphrases and candidate keyphrase ranking. For absent keyphrases, our Keyphrase-Focused BART achieved new state-of-the-art score on F1@5 in two out of five keyphrase generation benchmark datasets.