Automatic Summarization of Meeting Data: A Feasibility Study

Abstract

The disclosure of audio-visual meeting recordings is a new challenging domain studied by several large scale research projects in Europe and the US. Automatic meeting summarization is one of the functionalities studied. In this paper we report the results of a feasibility study on a subtask, namely the summarization of meeting transcripts. A Maximum Entropy based extractive summarization system using a mix of 15 features improved the performance of a baseline system selecting all utterances longer than 10 words with 20% (F-measure). However, stronger contextual awareness seems to be necessary in order to reduce the precision of the summarizer. The study required the creation of reference extractive summaries, which is documented in the paper.