A Sliding-Window Approach to Automatic Creation of Meeting Minutes
This work addresses the challenge of creating meeting minutes for virtual meetings, which is an incremental improvement in automated summarization for domain-specific applications.
The paper tackles the problem of automatically generating meeting minutes from lengthy, unstructured spoken transcripts by proposing a sliding-window approach combined with a neural abstractive summarizer to identify salient content. It evaluates the method on natural meeting conversations, comparing human and automatic transcripts to assess how well the summarizer captures key information.
Meeting minutes record any subject matters discussed, decisions reached and actions taken at meetings. The importance of minuting cannot be overemphasized in a time when a significant number of meetings take place in the virtual space. In this paper, we present a sliding window approach to automatic generation of meeting minutes. It aims to tackle issues associated with the nature of spoken text, including lengthy transcripts and lack of document structure, which make it difficult to identify salient content to be included in the meeting minutes. Our approach combines a sliding window and a neural abstractive summarizer to navigate through the transcripts to find salient content. The approach is evaluated on transcripts of natural meeting conversations, where we compare results obtained for human transcripts and two versions of automatic transcripts and discuss how and to what extent the summarizer succeeds at capturing salient content.