Dialogue Act Sequence Labeling using Hierarchical encoder with CRF

TL;DR

This paper introduces a hierarchical neural network with CRF for dialogue act recognition, improving accuracy on benchmark datasets by modeling dependencies among dialogue acts and utterances.

Contribution

The work presents a novel hierarchical LSTM-CRF model that captures multi-level representations and label dependencies for dialogue act sequence labeling.

Findings

Achieved 2.2% and 4.1% accuracy improvements on two datasets.

Effectively models label and utterance dependencies in dialogues.

Performs well despite noisy training data.

Abstract

Dialogue Act recognition associate dialogue acts (i.e., semantic labels) to utterances in a conversation. The problem of associating semantic labels to utterances can be treated as a sequence labeling problem. In this work, we build a hierarchical recurrent neural network using bidirectional LSTM as a base unit and the conditional random field (CRF) as the top layer to classify each utterance into its corresponding dialogue act. The hierarchical network learns representations at multiple levels, i.e., word level, utterance level, and conversation level. The conversation level representations are input to the CRF layer, which takes into account not only all previous utterances but also their dialogue acts, thus modeling the dependency among both, labels and utterances, an important consideration of natural dialogue. We validate our approach on two different benchmark data sets, Switchboard and Meeting Recorder Dialogue Act, and show performance improvement over the state-of-the-art methods by $2.2\%$ and $4.1\%$ absolute points, respectively. It is worth noting that the inter-annotator agreement on Switchboard data set is $84\%$, and our method is able to achieve the accuracy of about $79\%$ despite being trained on the noisy data.