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

03/02/2020
by   Hengyi Cai, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/06/2020

Data Manipulation: Towards Effective Instance Learning for Neural Dialogue Generation via Learning to Augment and Reweight

Current state-of-the-art neural dialogue models learn from human convers...
research
04/26/2020

Multi-Domain Dialogue Acts and Response Co-Generation

Generating fluent and informative responses is of critical importance fo...
research
07/30/2022

Dynamically Retrieving Knowledge via Query Generation for informative dialogue response

Knowledge-driven dialogue generation has recently made remarkable breakt...
research
06/03/2019

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

In this paper, a novel Generation-Evaluation framework is developed for ...
research
05/27/2020

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

Recently, neural network based dialogue systems have become ubiquitous i...
research
09/13/2019

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

Neural dialogue models have been widely adopted in various chatbot appli...
research
12/31/2020

Refine and Imitate: Reducing Repetition and Inconsistency in Persuasion Dialogues via Reinforcement Learning and Human Demonstration

Despite the recent success of large-scale language models on various dow...

Please sign up or login with your details

Forgot password? Click here to reset