Application of Machine Learning Algorithms for Automatic Knowledge Acquisition and Readability Analysis Technical Report

A large knowledge base is a prerequisite for a lot of tasks in natural language processing (NLP). To build a handcrafted knowledge base, which is applicable to real world scenarios, a vast amount of effort is required. Furthermore, experts are needed with a strong background in linguistics, artificial intelligence and knowledge representation which may not be available to the extent necessary (knowledge acquisition bottleneck). For these reasons, machine learning techniques are widely used to construct a knowledge base automatically. Learning techniques are also relevant to many other areas, e.g., for readability analysis. In the latter area, a lot of work is needed to find the optimal settings for a readability formula and it usually involves a large amount of trial and error iterations. Thus, it is preferable to learn the necessary parameter settings automatically. This report investigates the application of machine learning techniques in both areas. Finally, several freely available machine learning tools, which can be employed to accomplish both tasks, are introduced and compared with each other.