Automatic Creation of Domain Templates

Recently, many Natural Language Processing (NLP) applications have improved the quality of their output by using various machine learning tech- niques to mine Information Extraction (IE) patterns for capturing information from the input text. Cur- rently, to mine IE patterns one should know in ad- vance the type of the information that should be captured by these patterns. In this work we pro- pose a novel methodology for corpus analysis based on cross-examination of several document collec- tions representing different instances of the same domain. We show that this methodology can be used for automatic domain template creation. As the problem of automatic domain template creation is rather new, there is no well-defined procedure for the evaluation of the domain template quality. Thus, we propose a methodology for identifying what in- formation should be present in the template. Using this information we evaluate the automatically cre- ated domain templates through the text snippets re- trieved according to the created templates.