Learning a Matching Model with Co-teaching for Multi-turn Response Selection in Retrieval-based Dialogue Systems
arXiv:1906.04413
Abstract
We study learning of a matching model for response selection in retrieval-based dialogue systems. The problem is equally important with designing the architecture of a model, but is less explored in existing literature. To learn a robust matching model from noisy training data, we propose a general co-teaching framework with three specific teaching strategies that cover both teaching with loss functions and teaching with data curriculum. Under the framework, we simultaneously learn two matching models with independent training sets. In each iteration, one model transfers the knowledge learned from its training set to the other model, and at the same time receives the guide from the other model on how to overcome noise in training. Through being both a teacher and a student, the two models learn from each other and get improved together. Evaluation results on two public data sets indicate that the proposed learning approach can generally and significantly improve the performance of existing matching models.
References in corpus (10)
- Distributed Representations of Words and Phrases and their Compositionality
- A Neural Conversational Model
- Convolutional Neural Network Architectures for Matching Natural Language Sentences
- Topic Aware Neural Response Generation
- Personalizing Dialogue Agents: I have a dog, do you have pets too?
- An Information Retrieval Approach to Short Text Conversation
- Learning to Teach with Dynamic Loss Functions
- Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation
- Syntax-based Deep Matching of Short Texts
- Learning Matching Models with Weak Supervision for Response Selection in Retrieval-based Chatbots