Learning Matching Models with Weak Supervision for Response Selection in Retrieval-based Chatbots
arXiv:1805.02333
Abstract
We propose a method that can leverage unlabeled data to learn a matching model for response selection in retrieval-based chatbots. The method employs a sequence-to-sequence architecture (Seq2Seq) model as a weak annotator to judge the matching degree of unlabeled pairs, and then performs learning with both the weak signals and the unlabeled data. Experimental results on two public data sets indicate that matching models get significant improvements when they are learned with the proposed method.
arXiv commentaccepted by ACL 2018 as a short paper
References in corpus (9)
- Distilling the Knowledge in a Neural Network
- A Neural Conversational Model
- Convolutional Neural Network Architectures for Matching Natural Language Sentences
- Topic Aware Neural Response Generation
- Hierarchical Recurrent Attention Network for Response Generation
- From Eliza to XiaoIce: Challenges and Opportunities with Social Chatbots
- Syntax-based Deep Matching of Short Texts
- Avoiding Your Teacher's Mistakes: Training Neural Networks with Controlled Weak Supervision
- Fidelity-Weighted Learning