Dialogue Act Classification with Context-Aware Self-Attention

TL;DR

This paper introduces a context-aware self-attention mechanism combined with hierarchical RNNs for dialogue act classification, significantly improving accuracy on standard datasets by effectively capturing utterance semantics.

Contribution

It presents a novel combination of context-aware self-attention with hierarchical RNNs, advancing dialogue act classification performance over existing methods.

Findings

Significant improvement on the SwDA Corpus

Effective at capturing utterance-level semantics

Maintains high accuracy across evaluations

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.