Generating Personalized Dialogue via Multi-Task Meta-Learning
arXiv:2108.03377
Abstract
Conventional approaches to personalized dialogue generation typically require a large corpus, as well as predefined persona information. However, in a real-world setting, neither a large corpus of training data nor persona information are readily available. To address these practical limitations, we propose a novel multi-task meta-learning approach which involves training a model to adapt to new personas without relying on a large corpus, or on any predefined persona information. Instead, the model is tasked with generating personalized responses based on only the dialogue context. Unlike prior work, our approach leverages on the provided persona information only during training via the introduction of an auxiliary persona reconstruction task. In this paper, we introduce 2 frameworks that adopt the proposed multi-task meta-learning approach: the Multi-Task Meta-Learning (MTML) framework, and the Alternating Multi-Task Meta-Learning (AMTML) framework. Experimental results show that utilizing MTML and AMTML results in dialogue responses with greater persona consistency.
arXiv commentAccepted at SemDial 2021 (PotsDial 2021)
References in corpus (8)
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Prototypical Networks for Few-shot Learning
- How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
- On First-Order Meta-Learning Algorithms
- TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents
- Personalized Dialogue Generation with Diversified Traits
- Generating Persona Consistent Dialogues by Exploiting Natural Language Inference
- Personalization in Goal-Oriented Dialog