Enhancing Keyphrase Generation by BART Finetuning with Splitting and Shuffling
This work addresses the challenge of generating absent keyphrases in keyphrase generation tasks, which is important for improving document summarization and information retrieval, but it is incremental as it builds on existing BART models with specific modifications.
The paper tackled the problem of generating absent keyphrases in text by proposing Keyphrase-Focused BART, which uses separate BART models for present and absent keyphrases, along with shuffling and ranking techniques. It achieved new state-of-the-art F1@5 scores on two out of five benchmark datasets for absent keyphrases.
Keyphrase generation is a task of identifying a set of phrases that best repre-sent the main topics or themes of a given text. Keyphrases are dividend int pre-sent and absent keyphrases. Recent approaches utilizing sequence-to-sequence models show effectiveness on absent keyphrase generation. However, the per-formance is still limited due to the hardness of finding absent keyphrases. In this paper, we propose Keyphrase-Focused BART, which exploits the differ-ences between present and absent keyphrase generations, and performs fine-tuning 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 gen-eration benchmark datasets.