Open information extraction from texts. Part II. Extraction of semantic relations using unsupervised machine learning

In this paper, we discuss open information extraction from natural language texts. We present the approach to extraction of semantic relations using unsupervised machine learning. The presented approach is based on deep clustering methods in which clusterization algorithm is integrated in multi-layer autoencoder neural network. This method allows to generalize surface relations (triplets) into semantic relations. This paper also provides the method of surface relation extraction.