AUTOMATIC INFORMATION EXTRACTION FROM TEXT

Abstract

We present a method for automatic extract the hyponym-hypernym relations from the text data. In previous years many researchers were worked on this system but they use some pre-encoded knowledge and patterns for implementing this type of system. But this not that much use when we think about extracting more relations or discovering any new pattern. This type of system discovered one more risk which is once we use the predefined pattern and if this pattern failed to produce new pattern then all most all operation will fail due to the previous wrong pattern. The researcher was used semi-supervised machine learning approach for introducing such kind of information extraction system but this paper focuses on converting the semi-supervised machine learning approach into unsupervised machine learning approach for fully automatic extracting information from text. This paper is trying to focus on these previous issues. The paper focuses on two main objectives. (i) Avoid pre-encoded pattern for more efficiency. (ii) Define a method for automatically extracting useful relationships from an unsupervised machine learning approach. We demonstrate a machine learning approach and, especially, at different levels and in different ways, can be used to create a practical IE system. We unsupervised machine learning approach gives the better result than semi-supervised machine learning approach in term of information extraction.