%0 Conference Paper %1 Ciravegna:2001:AIE:1642194.1642261 %A Ciravegna, Fabio %B Proceedings of the 17th international joint conference on Artificial intelligence - Volume 2 %C San Francisco, CA, USA %D 2001 %I Morgan Kaufmann Publishers Inc. %K extraction induction information learning pattern %P 1251--1256 %T Adaptive information extraction from text by rule induction and generalisation %U http://eprints.aktors.org/118/01/IJCAI01.pdf %X (LP)² is a covering algorithm for adaptive Information Extraction from text (IE). It induces symbolic rules that insert SGML tags into texts by learning from examples found in a user-defined tagged corpus. Training is performed in two steps: initially a set of tagging rules is learned; then additional rules are induced to correct mistakes and imprecision in tagging. Induction is performed by bottom-up generalization of examples in the training corpus. Shallow knowledge about Natural Language Processing (NLP) is used in the generalization process. The algorithm has a considerable success story. From a scientific point of view, experiments report excellent results with respect to the current state of the art on two publicly available corpora. From an application point of view, a successful industrial IE tool has been based on (LP)². Real world applications have been developed and licenses have been released to external companies for building other applications. This paper presents (LP)², experimental results and applications, and discusses the role of shallow NLP in rule induction. %@ 1-55860-812-5, 978-1-558-60812-2

@inproceedings{Ciravegna:2001:AIE:1642194.1642261, abstract = {(LP)² is a covering algorithm for adaptive Information Extraction from text (IE). It induces symbolic rules that insert SGML tags into texts by learning from examples found in a user-defined tagged corpus. Training is performed in two steps: initially a set of tagging rules is learned; then additional rules are induced to correct mistakes and imprecision in tagging. Induction is performed by bottom-up generalization of examples in the training corpus. Shallow knowledge about Natural Language Processing (NLP) is used in the generalization process. The algorithm has a considerable success story. From a scientific point of view, experiments report excellent results with respect to the current state of the art on two publicly available corpora. From an application point of view, a successful industrial IE tool has been based on (LP)². Real world applications have been developed and licenses have been released to external companies for building other applications. This paper presents (LP)², experimental results and applications, and discusses the role of shallow NLP in rule induction.}, acmid = {1642261}, added-at = {2012-10-11T17:00:22.000+0200}, address = {San Francisco, CA, USA}, author = {Ciravegna, Fabio}, biburl = {https://www.bibsonomy.org/bibtex/25eb346593c6330ee742947824e75e710/jil}, booktitle = {Proceedings of the 17th international joint conference on Artificial intelligence - Volume 2}, description = {Adaptive information extraction from text by rule induction and generalisation}, interhash = {8e97c7bdb4db3c8144c32849b12b9714}, intrahash = {5eb346593c6330ee742947824e75e710}, isbn = {1-55860-812-5, 978-1-558-60812-2}, keywords = {extraction induction information learning pattern}, location = {Seattle, WA, USA}, numpages = {6}, pages = {1251--1256}, publisher = {Morgan Kaufmann Publishers Inc.}, series = {IJCAI'01}, timestamp = {2013-11-23T20:11:51.000+0100}, title = {Adaptive information extraction from text by rule induction and generalisation}, url = {http://eprints.aktors.org/118/01/IJCAI01.pdf}, year = 2001 }