An Empirical Analysis of Text Summarization Approaches for Automatic Minuting

A significant portion of the working population has their mainstream interaction virtually these days. Meetings are being organized and recorded daily in volumes likely exceeding what can be ever comprehended. With the deluge of meetings, it is important to identify and jot down the essential items discussed in the meeting, usually referred to as the minutes. The task of minuting is diverse and depends on the goals, style, procedure, and category of the meeting. Automatic Minuting is close to summarization; however, not exactly the same. In this work, we evaluate the current state-of-the-art summarization models for automatically generating meeting minutes. We provide empirical baselines to motivate the community to work on this very timely, relevant yet challenging problem. We conclude that off-the-shelf text summarization models are not the best candidates for generating minutes which calls for further research on meeting-specific summarization or minuting models. We found that Transformer-based models perform comparatively better than other categories of summarization algorithms; however, they are still far from generating a good multi-party meeting summary/minutes. We release our experimental code at https://github.com/ELITR/ Minuting_Baseline_Experiments.