CLApr 4, 2019

Dialogue Act Classification with Context-Aware Self-Attention

arXiv:1904.02594v21122 citations
Originality Incremental advance
AI Analysis

This work addresses dialogue act classification for conversational AI systems, representing an incremental advance over prior hierarchical deep learning approaches.

The authors tackled dialogue act classification by combining context-aware self-attention with hierarchical recurrent neural networks, achieving significant improvements over state-of-the-art results on the Switchboard Dialogue Act Corpus.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes