Sequence-to-Sequence Learning for Task-oriented Dialogue with Dialogue State Representation
arXiv:1806.04441
Abstract
Classic pipeline models for task-oriented dialogue system require explicit modeling the dialogue states and hand-crafted action spaces to query a domain-specific knowledge base. Conversely, sequence-to-sequence models learn to map dialogue history to the response in current turn without explicit knowledge base querying. In this work, we propose a novel framework that leverages the advantages of classic pipeline and sequence-to-sequence models. Our framework models a dialogue state as a fixed-size distributed representation and use this representation to query a knowledge base via an attention mechanism. Experiment on Stanford Multi-turn Multi-domain Task-oriented Dialogue Dataset shows that our framework significantly outperforms other sequence-to-sequence based baseline models on both automatic and human evaluation.
arXiv commentTo appear at COLING 2018
References in corpus (6)
- Sequence to Sequence Learning with Neural Networks
- Relevance of Unsupervised Metrics in Task-Oriented Dialogue for Evaluating Natural Language Generation
- Why We Need New Evaluation Metrics for NLG
- A User Simulator for Task-Completion Dialogues
- An End-to-End Trainable Neural Network Model with Belief Tracking for Task-Oriented Dialog
- End-to-End Task-Completion Neural Dialogue Systems
Cited by in corpus (9)
- ReviewRobot: Explainable Paper Review Generation based on Knowledge Synthesis
- Dialogue State Induction Using Neural Latent Variable Models
- Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog
- Entity-Consistent End-to-end Task-Oriented Dialogue System with KB Retriever
- AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Models
- DialogAct2Vec: Towards End-to-End Dialogue Agent by Multi-Task Representation Learning
- Constraint based Knowledge Base Distillation in End-to-End Task Oriented Dialogs
- Contextualize Knowledge Bases with Transformer for End-to-end Task-Oriented Dialogue Systems
- Don't be Contradicted with Anything! CI-ToD: Towards Benchmarking Consistency for Task-oriented Dialogue System