A Bag of Tricks for Dialogue Summarization
Muhammad Khalifa, Miguel Ballesteros, Kathleen R. McKeown · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · 2021
Dialogue summarization comes with its own peculiar challenges as opposed to news or scientific articles summarization.In this work, we explore four different challenges of the task: handling and differentiating parts of the dialogue belonging to multiple speakers, negation understanding, reasoning about the situation, and informal language understanding.Using a pretrained sequence-to-sequence language model, we explore speaker name substitution, negation scope highlighting, multi-task learning with relevant tasks, and pretraining on in-domain data.Our experiments show that our proposed techniques indeed improve summarization performance, outperforming strong baselines.