Unsupervised Technique To Conversational Machine Reading
This addresses the tedious and error-prone process of creating labeled datasets for CMR, offering a more efficient approach for developers and researchers in natural language processing.
The paper tackles the problem of conversational machine reading (CMR) by introducing an unsupervised learning technique to avoid the need for manually labeled datasets, reporting improvements of 3.3% in micro averaged accuracy and 1.4% in macro averaged accuracy compared to the best existing supervised tool.
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.