Abstractive Meeting Summarization UsingDependency Graph Fusion
This addresses the need for better automated summarization tools for meeting transcripts, though it appears incremental as it builds on existing sentence fusion techniques.
The paper tackled the problem of poor extractive summaries for meeting conversations by proposing an abstractive summarization method that fuses important content from multiple utterances using integer linear programming, resulting in more informative summaries than baselines.
Automatic summarization techniques on meeting conversations developed so far have been primarily extractive, resulting in poor summaries. To improve this, we propose an approach to generate abstractive summaries by fusing important content from several utterances. Any meeting is generally comprised of several discussion topic segments. For each topic segment within a meeting conversation, we aim to generate a one sentence summary from the most important utterances using an integer linear programming-based sentence fusion approach. Experimental results show that our method can generate more informative summaries than the baselines.