Unsupervised Technique To Conversational Machine Reading

TL;DR

This paper presents an unsupervised learning approach for conversational machine reading, reducing reliance on labeled data and improving accuracy over supervised methods in rule extraction and entailment tasks.

Contribution

It introduces an unsupervised framework for CMR that enhances rule extraction and entailment modules, outperforming supervised techniques in accuracy.

Findings

3.3% improvement in micro accuracy

1.4% improvement in macro accuracy

Reduces need for manual labeling

Abstract

Conversational machine reading (CMR) tools have seen a rapid progress in the recent past. The current existing tools rely on the supervised learning technique which require labeled dataset for their training. The supervised technique necessitates that for every new rule text, a manually labeled dataset must be created. This is tedious and error prone. This paper introduces and demonstrates how unsupervised learning technique can be applied in the development of CMR. Specifically, we demonstrate how unsupervised learning can be used in rule extraction and entailment modules of CMR. Compared to the current best CMR tool, our developed framework reports 3.3% improvement in micro averaged accuracy and 1.4 % improvement in macro averaged accuracy.