Neural Assistant: Joint Action Prediction, Response Generation, and Latent Knowledge Reasoning

Abstract

Task-oriented dialog presents a difficult challenge encompassing multiple problems including multi-turn language understanding and generation, knowledge retrieval and reasoning, and action prediction. Modern dialog systems typically begin by converting conversation history to a symbolic object referred to as belief state by using supervised learning. The belief state is then used to reason on an external knowledge source whose result along with the conversation history is used in action prediction and response generation tasks independently. Such a pipeline of individually optimized components not only makes the development process cumbersome but also makes it non-trivial to leverage session-level user reinforcement signals. In this paper, we develop Neural Assistant: a single neural network model that takes conversation history and an external knowledge source as input and jointly produces both text response and action to be taken by the system as output. The model learns to reason on the provided knowledge source with weak supervision signal coming from the text generation and the action prediction tasks, hence removing the need for belief state annotations. In the MultiWOZ dataset, we study the effect of distant supervision, and the size of knowledge base on model performance. We find that the Neural Assistant without belief states is able to incorporate external knowledge information achieving higher factual accuracy scores compared to Transformer. In settings comparable to reported baseline systems, Neural Assistant when provided with oracle belief state significantly improves language generation performance.

References in corpus (8)

• A Neural Conversational Model
• End-To-End Memory Networks
• Optimizing Dialogue Management with Reinforcement Learning: Experiments with the NJFun System
• Personalizing Dialogue Agents: I have a dog, do you have pets too?
• Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems
• Global-to-local Memory Pointer Networks for Task-Oriented Dialogue
• Latent Intention Dialogue Models
• Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning

Cited by in corpus (7)

• A Simple Language Model for Task-Oriented Dialogue
• CoCo: Controllable Counterfactuals for Evaluating Dialogue State Trackers
• BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modeling
• MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems
• How To Evaluate Your Dialogue System: Probe Tasks as an Alternative for Token-level Evaluation Metrics
• Pretraining the Noisy Channel Model for Task-Oriented Dialogue
• Do Encoder Representations of Generative Dialogue Models Encode Sufficient Information about the Task ?