Narrate Dialogues for Better Summarization
Ruochen Xu, Chenguang Zhu, Michael Zeng · 2022
Dialogue summarization models aim to generate a concise and accurate summary for multiparty dialogue.The complexity of dialogue, including coreference, dialogue acts, and interspeaker interactions bring unique challenges to dialogue summarization.Most recent neural models achieve state-of-art performance following the pretrain-then-finetune recipe, where the large-scale language model (LLM) is pretrained on large-scale single-speaker written text, but later finetuned on multi-speaker dialogue text.To mitigate the gap between pretraining and finetuning, we propose several approaches to convert the dialogue into a third-person narrative style and show that the narration serves as a valuable annotation for LLMs.Empirical results on three benchmark datasets show our simple approach achieves higher scores on the ROUGE and a factual correctness metric.