Learning to Learn End-to-End Goal-Oriented Dialog From Related Dialog Tasks

For each goal-oriented dialog task of interest, large amounts of data need to be collected for end-to-end learning of a neural dialog system. Collecting that data is a costly and time-consuming process. Instead, we show that we can use only a small amount of data, supplemented with data from a related dialog task. Naively learning from related data fails to improve performance as the related data can be inconsistent with the target task. We describe a meta-learning based method that selectively learns from the related dialog task data. Our approach leads to significant accuracy improvements in an example dialog task.

[1]  Boi Faltings,et al.  Personalization in Goal-Oriented Dialog , 2017, ArXiv.

[2]  Honglak Lee,et al.  How Should an Agent Practice? , 2019, AAAI.

[3]  David Silver,et al.  Meta-Gradient Reinforcement Learning , 2018, NeurIPS.

[4]  Jian Sun,et al.  Learning Low-Resource End-To-End Goal-Oriented Dialog for Fast and Reliable System Deployment , 2020, ACL.

[5]  José M. F. Moura,et al.  Adversarial Multiple Source Domain Adaptation , 2018, NeurIPS.

[6]  Jaime G. Carbonell,et al.  Characterizing and Avoiding Negative Transfer , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Christopher D. Manning,et al.  Key-Value Retrieval Networks for Task-Oriented Dialogue , 2017, SIGDIAL Conference.

[8]  David Vandyke,et al.  A Network-based End-to-End Trainable Task-oriented Dialogue System , 2016, EACL.

[9]  ChengXiang Zhai,et al.  Instance Weighting for Domain Adaptation in NLP , 2007, ACL.

[10]  Renjie Liao,et al.  Understanding Short-Horizon Bias in Stochastic Meta-Optimization , 2018, ICLR.

[11]  Michael Zeng,et al.  Meta Dialogue Policy Learning , 2020, ArXiv.

[12]  Carlos D. Castillo,et al.  Generate to Adapt: Aligning Domains Using Generative Adversarial Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[13]  Pascale Fung,et al.  MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems , 2020, EMNLP.

[14]  David Vandyke,et al.  Multi-domain Neural Network Language Generation for Spoken Dialogue Systems , 2016, NAACL.

[15]  Jason Weston,et al.  Learning End-to-End Goal-Oriented Dialog , 2016, ICLR.

[16]  Jason Weston,et al.  End-To-End Memory Networks , 2015, NIPS.

[17]  Zhou Yu,et al.  Domain Adaptive Dialog Generation via Meta Learning , 2019, ACL.

[18]  Sergey Levine,et al.  Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks , 2017, ICML.

[19]  Misha Denil,et al.  Learned Optimizers that Scale and Generalize , 2017, ICML.

[20]  Jaime G. Carbonell,et al.  Completely Heterogeneous Transfer Learning with Attention - What And What Not To Transfer , 2017, IJCAI.

[21]  Jianmin Wang,et al.  Partial Adversarial Domain Adaptation , 2018, ECCV.

[22]  Boi Faltings,et al.  Meta-Learning for Low-resource Natural Language Generation in Task-oriented Dialogue Systems , 2019, IJCAI.

[23]  Pascale Fung,et al.  Personalizing Dialogue Agents via Meta-Learning , 2019, ACL.