Learning Matching Models with Weak Supervision for Response Selection in Retrieval-based Chatbots

TL;DR

This paper introduces a weak supervision approach using Seq2Seq models to improve response matching in retrieval-based chatbots by leveraging unlabeled data, leading to significant performance gains.

Contribution

It presents a novel method that employs Seq2Seq models as weak annotators to enhance matching models with unlabeled data in chatbot response selection.

Findings

Significant performance improvements on two public datasets.

Effective utilization of unlabeled data through weak supervision.

Enhanced response matching accuracy in retrieval-based chatbots.

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.