Meta Dialogue Policy Learning

By Yumo Xu, Chenguang Zhu, Baolin Peng, Michael Zeng. 2020

8 citations recorded by the source corpus.

Dialog policy determines the next-step actions for agents and hence is central to a dialogue system. However, when migrated to novel domains with little data, a policy model can fail to adapt due to insufficient interactions with the new environment. We propose Deep Transferable Q-Network (DTQN) to utilize shareable low-level signals between domains, such as dialogue acts and slots. We decompose the state and action representation space into feature subspaces corresponding to these low-level components to facilitate cross-domain knowledge transfer. Furthermore, we embed DTQN in a meta-learning framework and introduce Meta-DTQN with a dual-replay mechanism to enable effective off-policy training and adaptation. In experiments, our model outperforms baseline models in terms of both success rate and dialogue efficiency on the multi-domain dialogue dataset MultiWOZ 2.0.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Dynamic Dialogue Policy for Continual Reinforcement Learning (2022, methodology): “Xu et al. (2020) go a step further in that direction.”
Language Models as Few-Shot Learner for Task-Oriented Dialogue Systems (2020, background): “Finally, several meta-learning approaches have been proposed for DP (Xu et al., 2020), NLG/ACT (Mi et al., 2019), pipelined endto-end models (Qian and Yu, 2019) and personalized dialogue systems (Madotto et al., 2019).”
Dynamic Dialogue Policy Transformer for Continual Reinforcement Learning (2022, methodology): “Xu et al. (2020) go a step further in that direction.”