%0 Conference Paper %1 tengli2004learning %A Tengli, Ashwin %A Yang, Yiming %A Ma, Nian Li %B Proceedings of the 20th international conference on Computational Linguistics %C Stroudsburg, PA, USA %D 2004 %I Association for Computational Linguistics %K INWERO extraction information learning table web %R 10.3115/1220355.1220497 %T Learning table extraction from examples %U http://dx.doi.org/10.3115/1220355.1220497 %X Information extraction from tables in web pages is a challenging problem due to the diverse nature of table formats and the vocabulary variants in attribute names. This paper presents a new approach to automated table extraction that exploits formatting cues in semi-structured HTML tables, learns lexical variants from training examples and uses a vector space model to deal with non-exact matches among labels. We conducted experiments with this method on a set of tables collected from 157 university web sites, and obtained the information extraction performance of 91.4% in the Fl-measure, showing the effectiveness of the combined use of structural table parsing and example-based label learning.

@inproceedings{tengli2004learning, abstract = {Information extraction from tables in web pages is a challenging problem due to the diverse nature of table formats and the vocabulary variants in attribute names. This paper presents a new approach to automated table extraction that exploits formatting cues in semi-structured HTML tables, learns lexical variants from training examples and uses a vector space model to deal with non-exact matches among labels. We conducted experiments with this method on a set of tables collected from 157 university web sites, and obtained the information extraction performance of 91.4% in the Fl-measure, showing the effectiveness of the combined use of structural table parsing and example-based label learning.}, acmid = {1220497}, added-at = {2012-09-20T14:54:59.000+0200}, address = {Stroudsburg, PA, USA}, articleno = {987}, author = {Tengli, Ashwin and Yang, Yiming and Ma, Nian Li}, biburl = {https://www.bibsonomy.org/bibtex/29b4568ebe3e9995185a37e5de2846053/porta}, booktitle = {Proceedings of the 20th international conference on Computational Linguistics}, doi = {10.3115/1220355.1220497}, groups = {public}, interhash = {c4d46d3f1fed4c9d8830181b9c02d73c}, intrahash = {9b4568ebe3e9995185a37e5de2846053}, keywords = {INWERO extraction information learning table web}, location = {Geneva, Switzerland}, publisher = {Association for Computational Linguistics}, series = {COLING '04}, timestamp = {2013-03-01T23:28:03.000+0100}, title = {Learning table extraction from examples}, url = {http://dx.doi.org/10.3115/1220355.1220497}, username = {porta}, year = 2004 }