Learning Matching Models with Weak Supervision for Response Selection in Retrieval-based Chatbots
This work addresses the challenge of data scarcity for training response selection models in chatbots, though it is incremental as it builds on existing weak supervision techniques.
The paper tackles the problem of learning matching models for response selection in retrieval-based chatbots by leveraging unlabeled data with weak supervision from a Seq2Seq model, resulting in significant improvements on two public datasets.
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.