Dialogue Act Classification in Group Chats with DAG-LSTMs

Abstract

Dialogue act (DA) classification has been studied for the past two decades and has several key applications such as workflow automation and conversation analytics. Researchers have used, to address this problem, various traditional machine learning models, and more recently deep neural network models such as hierarchical convolutional neural networks (CNNs) and long short-term memory (LSTM) networks. In this paper, we introduce a new model architecture, directed-acyclic-graph LSTM (DAG-LSTM) for DA classification. A DAG-LSTM exploits the turn-taking structure naturally present in a multi-party conversation, and encodes this relation in its model structure. Using the STAC corpus, we show that the proposed method performs roughly 0.8% better in accuracy and 1.2% better in macro-F1 score when compared to existing methods. The proposed method is generic and not limited to conversation applications.

arXiv commentAppeared in SIGIR 2019 Workshop on Conversational Interaction Systems

References in corpus (12)

• Adam: A Method for Stochastic Optimization
• Enhanced LSTM for Natural Language Inference
• Dialogue Act Modeling for Automatic Tagging and Recognition of Conversational Speech
• DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset
• Recurrent Convolutional Neural Networks for Discourse Compositionality
• Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning
• Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems
• Tree-to-tree Neural Networks for Program Translation
• Jointly Learning Sentence Embeddings and Syntax with Unsupervised Tree-LSTMs
• The Influence of Context on Dialogue Act Recognition
• Exploiting Sentence and Context Representations in Deep Neural Models for Spoken Language Understanding
• DAG-based Long Short-Term Memory for Neural Word Segmentation