Dialog State Tracking: A Neural Reading Comprehension Approach

Abstract

Dialog state tracking is used to estimate the current belief state of a dialog given all the preceding conversation. Machine reading comprehension, on the other hand, focuses on building systems that read passages of text and answer questions that require some understanding of passages. We formulate dialog state tracking as a reading comprehension task to answer the question $whatisthestateofthecurrentdialog?$ after reading conversational context. In contrast to traditional state tracking methods where the dialog state is often predicted as a distribution over a closed set of all the possible slot values within an ontology, our method uses a simple attention-based neural network to point to the slot values within the conversation. Experiments on MultiWOZ-2.0 cross-domain dialog dataset show that our simple system can obtain similar accuracies compared to the previous more complex methods. By exploiting recent advances in contextual word embeddings, adding a model that explicitly tracks whether a slot value should be carried over to the next turn, and combining our method with a traditional joint state tracking method that relies on closed set vocabulary, we can obtain a joint-goal accuracy of $47.33\%$ on the standard test split, exceeding current state-of-the-art by $11.75\%$**.

arXiv comment10 pages, to appear in Special Interest Group on Discourse and Dialogue (SIGDIAL) 2019 (ORAL)

References in corpus (8)

• Sequence to Sequence Learning with Neural Networks
• Teaching Machines to Read and Comprehend
• Bidirectional Attention Flow for Machine Comprehension
• SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering
• RACE: Large-scale ReAding Comprehension Dataset From Examinations
• An End-to-End Trainable Neural Network Model with Belief Tracking for Task-Oriented Dialog
• Global-Locally Self-Attentive Dialogue State Tracker
• Flexible and Scalable State Tracking Framework for Goal-Oriented Dialogue Systems

Cited by in corpus (10)

• CoCo: Controllable Counterfactuals for Evaluating Dialogue State Trackers
• Non-Autoregressive Dialog State Tracking
• From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gap
• MA-DST: Multi-Attention Based Scalable Dialog State Tracking
• A Hybrid Task-Oriented Dialog System with Domain and Task Adaptive Pretraining
• Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Tracking
• Alexa Conversations: An Extensible Data-driven Approach for Building Task-oriented Dialogue Systems
• Improving Limited Labeled Dialogue State Tracking with Self-Supervision
• Learn to Focus: Hierarchical Dynamic Copy Network for Dialogue State Tracking
• Efficient Dialogue State Tracking by Masked Hierarchical Transformer