Log In Sign Up

Learning from Easy to Complex: Adaptive Multi-curricula Learning for Neural Dialogue Generation

by   Hengyi Cai, et al.

Current state-of-the-art neural dialogue systems are mainly data-driven and are trained on human-generated responses. However, due to the subjectivity and open-ended nature of human conversations, the complexity of training dialogues varies greatly. The noise and uneven complexity of query-response pairs impede the learning efficiency and effects of the neural dialogue generation models. What is more, so far, there are no unified dialogue complexity measurements, and the dialogue complexity embodies multiple aspects of attributes—specificity, repetitiveness, relevance, etc. Inspired by human behaviors of learning to converse, where children learn from easy dialogues to complex ones and dynamically adjust their learning progress, in this paper, we first analyze five dialogue attributes to measure the dialogue complexity in multiple perspectives on three publicly available corpora. Then, we propose an adaptive multi-curricula learning framework to schedule a committee of the organized curricula. The framework is established upon the reinforcement learning paradigm, which automatically chooses different curricula at the evolving learning process according to the learning status of the neural dialogue generation model. Extensive experiments conducted on five state-of-the-art models demonstrate its learning efficiency and effectiveness with respect to 13 automatic evaluation metrics and human judgments.


page 1

page 2

page 3

page 4


Multi-Domain Dialogue Acts and Response Co-Generation

Generating fluent and informative responses is of critical importance fo...

Measuring and Improving Semantic Diversity of Dialogue Generation

Response diversity has become an important criterion for evaluating the ...

Know More about Each Other: Evolving Dialogue Strategy via Compound Assessment

In this paper, a novel Generation-Evaluation framework is developed for ...

Chat as Expected: Learning to Manipulate Black-box Neural Dialogue Models

Recently, neural network based dialogue systems have become ubiquitous i...

Say What I Want: Towards the Dark Side of Neural Dialogue Models

Neural dialogue models have been widely adopted in various chatbot appli...