WHORU: Improving Abstractive Dialogue Summarization with Personal Pronoun Resolution

With the abundance of conversations happening everywhere, dialogue summarization plays an increasingly important role in real world. However, dialogues inevitably involve many personal pronouns, which hinder performance existing models. This work proposes a framework named WHORU to inject external pronoun resolution (PPR) information into abstractive A simple and effective PPR method for domain is further proposed reduce time space consumption. Experiments demonstrated superiority methods. More importantly, achieves new SOTA results on SAMSum AMI datasets.