2019/04/04 by Vipul Raheja, Raheja, Vipul, Joel Tetreault +1 · 62 citations
Computer Science · #Artificial intelligence #Artificial neural network #Attention network #Computation and Language (cs.CL) #Computer science #Context (archaeology) #FOS: Computer and information sciences #Linguistics #Machine learning #Natural Language Processing Techniques #Natural language processing #Representation (politics) #Sequence labeling #Speech act #Speech and dialogue systems #Task (project management) #Topic Modeling #Utterance #cs.CL
paper · pdf · doi:10.48550/arxiv.1904.02594
published in arXiv (Cornell University) (Cornell University) · NAACL-HLT 2019. 7 pages, 3 figures
openalex publication_date 2019/04/04 · arxiv created 2019/05/06 · arxiv updated 2019/05/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.