Flexible and Scalable State Tracking Framework for Goal-Oriented Dialogue Systems

Abstract

Goal-oriented dialogue systems typically rely on components specifically developed for a single task or domain. This limits such systems in two different ways: If there is an update in the task domain, the dialogue system usually needs to be updated or completely re-trained. It is also harder to extend such dialogue systems to different and multiple domains. The dialogue state tracker in conventional dialogue systems is one such component - it is usually designed to fit a well-defined application domain. For example, it is common for a state variable to be a categorical distribution over a manually-predefined set of entities (Henderson et al., 2013), resulting in an inflexible and hard-to-extend dialogue system. In this paper, we propose a new approach for dialogue state tracking that can generalize well over multiple domains without incorporating any domain-specific knowledge. Under this framework, discrete dialogue state variables are learned independently and the information of a predefined set of possible values for dialogue state variables is not required. Furthermore, it enables adding arbitrary dialogue context as features and allows for multiple values to be associated with a single state variable. These characteristics make it much easier to expand the dialogue state space. We evaluate our framework using the widely used dialogue state tracking challenge data set (DSTC2) and show that our framework yields competitive results with other state-of-the-art results despite incorporating little domain knowledge. We also show that this framework can benefit from widely available external resources such as pre-trained word embeddings.

arXiv commentNIPS CONVAI Workshop 2018

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Sequence to Sequence Learning with Neural Networks
• Enriching Word Vectors with Subword Information
• Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning
• End-to-End Optimization of Task-Oriented Dialogue Model with Deep Reinforcement Learning
• An Attentional Neural Conversation Model with Improved Specificity
• Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems
• Generating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Models
• Dialog state tracking, a machine reading approach using Memory Network
• Multi-task learning for Joint Language Understanding and Dialogue State Tracking

Cited by in corpus (10)

• SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Tracking
• Dialog State Tracking: A Neural Reading Comprehension Approach
• Teacher-Student Framework Enhanced Multi-domain Dialogue Generation
• An End-to-End Dialogue State Tracking System with Machine Reading Comprehension and Wide & Deep Classification
• From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gap
• BERT-DST: Scalable End-to-End Dialogue State Tracking with Bidirectional Encoder Representations from Transformer
• DialogAct2Vec: Towards End-to-End Dialogue Agent by Multi-Task Representation Learning
• MTSS: Learn from Multiple Domain Teachers and Become a Multi-domain Dialogue Expert
• Comprehensive Study: How the Context Information of Different Granularity Affects Dialogue State Tracking?
• STN4DST: A Scalable Dialogue State Tracking based on Slot Tagging Navigation