Global-Locally Self-Attentive Dialogue State Tracker

Abstract

Dialogue state tracking, which estimates user goals and requests given the dialogue context, is an essential part of task-oriented dialogue systems. In this paper, we propose the Global-Locally Self-Attentive Dialogue State Tracker (GLAD), which learns representations of the user utterance and previous system actions with global-local modules. Our model uses global modules to share parameters between estimators for different types (called slots) of dialogue states, and uses local modules to learn slot-specific features. We show that this significantly improves tracking of rare states and achieves state-of-the-art performance on the WoZ and DSTC2 state tracking tasks. GLAD obtains 88.1% joint goal accuracy and 97.1% request accuracy on WoZ, outperforming prior work by 3.7% and 5.5%. On DSTC2, our model obtains 74.5% joint goal accuracy and 97.5% request accuracy, outperforming prior work by 1.1% and 1.0%.

ACL 2018. 10 pages, 5 figures. Source code: https://github.com/salesforce/glad

References in corpus (2)

• One Model To Learn Them All
• DCN+: Mixed Objective and Deep Residual Coattention for Question Answering

Cited by in corpus (25)

• The Natural Language Decathlon: Multitask Learning as Question Answering
• Coarse-grain Fine-grain Coattention Network for Multi-evidence Question Answering
• Global-to-local Memory Pointer Networks for Task-Oriented Dialogue
• Recent Advances and Challenges in Task-oriented Dialog System
• SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Tracking
• Dialog State Tracking: A Neural Reading Comprehension Approach
• Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention
• Toward Scalable Neural Dialogue State Tracking Model
• Efficient Dialogue State Tracking by Selectively Overwriting Memory
• MALA: Cross-Domain Dialogue Generation with Action Learning
• From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gap
• RTFM: Generalising to Novel Environment Dynamics via Reading
• Multi-Domain Dialogue Acts and Response Co-Generation
• Act-Aware Slot-Value Predicting in Multi-Domain Dialogue State Tracking
• Scalable and Accurate Dialogue State Tracking via Hierarchical Sequence Generation
• DialogAct2Vec: Towards End-to-End Dialogue Agent by Multi-Task Representation Learning
• A Context-Aware Hierarchical BERT Fusion Network for Multi-turn Dialog Act Detection
• MTSS: Learn from Multiple Domain Teachers and Become a Multi-domain Dialogue Expert
• CASA-NLU: Context-Aware Self-Attentive Natural Language Understanding for Task-Oriented Chatbots
• E3: Entailment-driven Extracting and Editing for Conversational Machine Reading
• Neural Dialogue State Tracking with Temporally Expressive Networks
• Parallel Interactive Networks for Multi-Domain Dialogue State Generation
• SIM: A Slot-Independent Neural Model for Dialogue State Tracking
• Learn to Focus: Hierarchical Dynamic Copy Network for Dialogue State Tracking
• Dialogue State Tracking with a Language Model using Schema-Driven Prompting