A Context-based Approach for Dialogue Act Recognition using Simple Recurrent Neural Networks

TL;DR

This paper introduces a context-based method using simple recurrent neural networks for dialogue act recognition, demonstrating that incorporating preceding utterances significantly improves classification accuracy on the Switchboard corpus.

Contribution

The paper proposes a novel context-aware approach with character-level language models for dialogue act recognition, addressing the limitations of previous utterance-level models.

Findings

Inclusion of preceding utterances improves detection accuracy.

Character-level language models effectively represent utterance context.

Significant performance gains on the Switchboard Dialogue Act corpus.

Abstract

Dialogue act recognition is an important part of natural language understanding. We investigate the way dialogue act corpora are annotated and the learning approaches used so far. We find that the dialogue act is context-sensitive within the conversation for most of the classes. Nevertheless, previous models of dialogue act classification work on the utterance-level and only very few consider context. We propose a novel context-based learning method to classify dialogue acts using a character-level language model utterance representation, and we notice significant improvement. We evaluate this method on the Switchboard Dialogue Act corpus, and our results show that the consideration of the preceding utterances as a context of the current utterance improves dialogue act detection.