Machine Learning of Ambiguous Sentences in Technical Manual for Tacit Knowledge Acquisition

Abstract

The objective of this study is to judge ambiguous sentences for mining tacit knowledge. This study was conducted with inspections and maintenance of railway rolling stock as the subject. To test the hypothesis that ambiguous sentences include tacit knowledge, we compared result of mining by human and by machine learning. We obtained the results that we can recognize the ambiguous sentences by machinery judgement with high accuracy. The most striking observation to emerge from this data analysis was that ambiguous sentences can identified not only by adjectives and adverbs but also nouns, post positional particle, or conjunctions.