共起を考慮した単語の特徴ベクトルの主成分回帰分析による推理小説の犯人推定

抄録

In recent years, there is an interpretability problem that even experts cannot explain the reasoning process of machine learning. A contest featuring interpretability, "First Knowledge Graph Reasoning Challenge 2018," was held in Tokyo. To learn the sense of word in the novel, a previous study proposed a method that was based on word embedding. However, it did not consider the flow of events. In this study, considering co-occurrence words, we propose a method using the principal components regression analysis of the feature vector of words.