DialogAct2Vec: Towards End-to-End Dialogue Agent by Multi-Task Representation Learning
arXiv:1911.04088
Abstract
In end-to-end dialogue modeling and agent learning, it is important to (1) effectively learn knowledge from data, and (2) fully utilize heterogeneous information, e.g., dialogue act flow and utterances. However, the majority of existing methods cannot simultaneously satisfy the two conditions. For example, rule definition and data labeling during system design take too much manual work, and sequence-to-sequence methods only model one-side utterance information. In this paper, we propose a novel joint end-to-end model by multi-task representation learning, which can capture the knowledge from heterogeneous information through automatically learning knowledgeable low-dimensional embeddings from data, named with DialogAct2Vec. The model requires little manual work for intervention in system design and we find that the multi-task learning can greatly improve the effectiveness of representation learning. Extensive experiments on a public dataset for restaurant reservation show that the proposed method leads to significant improvements against the state-of-the-art baselines on both the act prediction task and utterance prediction task.
Under review
References in corpus (12)
- A Convolutional Neural Network for Modelling Sentences
- Deep Reinforcement Learning for Dialogue Generation
- End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning
- BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems
- Global-Locally Self-Attentive Dialogue State Tracker
- Personalization in Goal-Oriented Dialog
- Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning
- Sequence-to-Sequence Learning for Task-oriented Dialogue with Dialogue State Representation
- Flexible and Scalable State Tracking Framework for Goal-Oriented Dialogue Systems
- An End-to-end Approach for Handling Unknown Slot Values in Dialogue State Tracking
- Multi-task Learning for Continuous Control
- Towards Universal Dialogue State Tracking