Abstractive Dialogue Summarization with Sentence-Gated Modeling Optimized by Dialogue Acts
arXiv:1809.05715
Abstract
Neural abstractive summarization has been increasingly studied, where the prior work mainly focused on summarizing single-speaker documents (news, scientific publications, etc). In dialogues, there are different interactions between speakers, which are usually defined as dialogue acts. The interactive signals may provide informative cues for better summarizing dialogues. This paper proposes to explicitly leverage dialogue acts in a neural summarization model, where a sentence-gated mechanism is designed for modeling the relationship between dialogue acts and the summary. The experiments show that our proposed model significantly improves the abstractive summarization performance compared to the state-of-the-art baselines on AMI meeting corpus, demonstrating the usefulness of the interactive signal provided by dialogue acts.
arXiv comment8 pages, accepted by SLT 2018
References in corpus (5)
- Dialogue Act Modeling for Automatic Tagging and Recognition of Conversational Speech
- Recurrent Convolutional Neural Networks for Discourse Compositionality
- Language as a Latent Variable: Discrete Generative Models for Sentence Compression
- Bottom-Up Abstractive Summarization
- Dialogue Act Tagging with Transformation-Based Learning