@inproceedings{64c028e1ad114e6e8a90b63d52df1019,
title = "Combining linguistic and statistical analysis to extract relations from web documents",
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 birth-date. 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 benefits of our approach by extensive experiments with our prototype system LEILA.",
keywords = "Machine Learning, Pattern Matching, Relation Extraction",
author = "Suchanek, \{Fabian M.\} and Georgiana Ifrim and Gerhard Weikum",
year = "2006",
month = jan,
day = "1",
doi = "10.1145/1150402.1150492",
language = "English",
isbn = "1595933395",
series = "Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",
publisher = "Association for Computing Machinery (ACM)",
pages = "712--717",
booktitle = "KDD 2006",
note = "KDD 2006: 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining ; Conference date: 20-08-2006 Through 23-08-2006",
}