Novel framework for dialogue summarization based on factual-statement fusion and dialogue segmentation.

Abstract

The explosive growth of dialogue data has aroused significant interest among scholars in abstractive dialogue summarization. In this paper, we propose a novel sequence-to-sequence framework called DS-SS (Dialogue Summarization with Factual-Statement Fusion and Dialogue Segmentation) for summarizing dialogues. The novelty of the DS-SS framework mainly lies in two aspects: 1) Factual statements are extracted from the source dialogue and combined with the source dialogue to perform the further dialogue encoding; and 2) A dialogue segmenter is trained and used to separate a dialogue to be encoded into several topic-coherent segments. Thanks to these two aspects, the proposed framework may better encode dialogues, thereby generating summaries exhibiting higher factual consistency and informativeness. Experimental results on two large-scale datasets SAMSum and DialogSum demonstrate the superiority of our framework over strong baselines, as evidenced by both automatic evaluation metrics and human evaluation.