Dialogue Act Classification with Context-Aware Self-Attention
arXiv:1904.02594
Abstract
Recent work in Dialogue Act classification has treated the task as a sequence labeling problem using hierarchical deep neural networks. We build on this prior work by leveraging the effectiveness of a context-aware self-attention mechanism coupled with a hierarchical recurrent neural network. We conduct extensive evaluations on standard Dialogue Act classification datasets and show significant improvement over state-of-the-art results on the Switchboard Dialogue Act (SwDA) Corpus. We also investigate the impact of different utterance-level representation learning methods and show that our method is effective at capturing utterance-level semantic text representations while maintaining high accuracy.
NAACL-HLT 2019. 7 pages, 3 figures
References in corpus (5)
- Distributed Representations of Sentences and Documents
- Dialogue Act Modeling for Automatic Tagging and Recognition of Conversational Speech
- Skip-Thought Vectors
- Bi-Directional Block Self-Attention for Fast and Memory-Efficient Sequence Modeling
- Multi-level Gated Recurrent Neural Network for Dialog Act Classification
Cited by in corpus (4)
- Local Contextual Attention with Hierarchical Structure for Dialogue Act Recognition
- MultiMediate '22: Backchannel Detection and Agreement Estimation in Group Interactions
- Persuasive Dialogue Understanding: the Baselines and Negative Results
- InterviewBot: Real-Time End-to-End Dialogue System to Interview Students for College Admission