%0 Conference Paper %1 Suchanek2006combining %A Suchanek, Fabian M. %A Ifrim, Georgiana %A Weikum, Gerhard %B 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2006) %D 2006 %K mpi nlp ontologylearning prontoLiterature %T Combining Linguistic and Statistical Analysis to Extract Relations from Web Documents %U http://www.mpi-inf.mpg.de/~suchanek/publications/kdd2006.pdf %X The World Wide Web provides a nearly endless source of knowledge, which is mostly given in natural language. A first step towards exploiting this data automatically could be to extract pairs of a given semantic relation from text documents -- for example all pairs of a person and her birthdate. One strategy for this task is to find text patterns that express the semantic relation, to generalize these patterns, and to apply them to a corpus to find new pairs. In this paper, we show that this approach profits significantly when deep linguistic structures are used instead of surface text patterns. We demonstrate how linguistic structures can be represented for machine learning, and we provide a theoretical analysis of the pattern matching approach. We show the practical relevance of our approach by extensive experiments with our prototype system LEILA.

@inproceedings{Suchanek2006combining, abstract = {The World Wide Web provides a nearly endless source of knowledge, which is mostly given in natural language. A first step towards exploiting this data automatically could be to extract pairs of a given semantic relation from text documents -- for example all pairs of a person and her birthdate. One strategy for this task is to find text patterns that express the semantic relation, to generalize these patterns, and to apply them to a corpus to find new pairs. In this paper, we show that this approach profits significantly when deep linguistic structures are used instead of surface text patterns. We demonstrate how linguistic structures can be represented for machine learning, and we provide a theoretical analysis of the pattern matching approach. We show the practical relevance of our approach by extensive experiments with our prototype system LEILA. }, added-at = {2007-06-22T15:15:42.000+0200}, author = {Suchanek, Fabian M. and Ifrim, Georgiana and Weikum, Gerhard}, biburl = {https://www.bibsonomy.org/bibtex/2582f0fbf28ea6d24eb5930ecb3b45bee/seb}, booktitle = {12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2006)}, interhash = {40279723d19a4a880b202ed5876ea70b}, intrahash = {582f0fbf28ea6d24eb5930ecb3b45bee}, keywords = {mpi nlp ontologylearning prontoLiterature}, timestamp = {2007-06-22T15:24:55.000+0200}, title = {Combining Linguistic and Statistical Analysis to Extract Relations from Web Documents}, url = {http://www.mpi-inf.mpg.de/~suchanek/publications/kdd2006.pdf}, year = 2006 }