Dialogue Act Tagging with Transformation-Based Learning

TL;DR

This paper applies Transformation-Based Learning to dialogue act tagging, introducing new features and strategies to improve efficiency and accuracy in recognizing dialogue acts.

Contribution

It introduces novel features, automatic cue construction methods, and efficiency strategies for TBL in dialogue act tagging, achieving state-of-the-art accuracy.

Findings

Achieves accuracy comparable to leading systems

Introduces effective dialogue act cues and feature extraction methods

Develops efficient training and confidence estimation strategies

Abstract

For the task of recognizing dialogue acts, we are applying the Transformation-Based Learning (TBL) machine learning algorithm. To circumvent a sparse data problem, we extract values of well-motivated features of utterances, such as speaker direction, punctuation marks, and a new feature, called dialogue act cues, which we find to be more effective than cue phrases and word n-grams in practice. We present strategies for constructing a set of dialogue act cues automatically by minimizing the entropy of the distribution of dialogue acts in a training corpus, filtering out irrelevant dialogue act cues, and clustering semantically-related words. In addition, to address limitations of TBL, we introduce a Monte Carlo strategy for training efficiently and a committee method for computing confidence measures. These ideas are combined in our working implementation, which labels held-out data as accurately as any other reported system for the dialogue act tagging task.