Towards End-to-End Learning for Efficient Dialogue Agent by Modeling Looking-ahead Ability
arXiv:1908.05408
Abstract
Learning an efficient manager of dialogue agent from data with little manual intervention is important, especially for goal-oriented dialogues. However, existing methods either take too many manual efforts (e.g. reinforcement learning methods) or cannot guarantee the dialogue efficiency (e.g. sequence-to-sequence methods). In this paper, we address this problem by proposing a novel end-to-end learning model to train a dialogue agent that can look ahead for several future turns and generate an optimal response to make the dialogue efficient. Our method is data-driven and does not require too much manual work for intervention during system design. We evaluate our method on two datasets of different scenarios and the experimental results demonstrate the efficiency of our model.
arXiv commentTo appear in Special Interest Group on Discourse and Dialogue (SIGDIAL) 2019 (ORAL)
References in corpus (12)
- Distributed Representations of Words and Phrases and their Compositionality
- Sequence to Sequence Learning with Neural Networks
- A Neural Conversational Model
- Individual and Domain Adaptation in Sentence Planning for Dialogue
- Why We Need New Evaluation Metrics for NLG
- A User Simulator for Task-Completion Dialogues
- End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning
- Continuously Learning Neural Dialogue Management
- BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems
- Personalization in Goal-Oriented Dialog
- Evaluating Prerequisite Qualities for Learning End-to-End Dialog Systems
- Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning