%0 Journal Article %1 Michelson2007Unsupervised %A Michelson, Matthew %A Knoblock, Craig %D 2007 %J International Journal on Document Analysis and Recognition %K badtext extraction %N 3 %P 211--226 %R http://dx.doi.org/10.1007/s10032-007-0052-2 %T Unsupervised information extraction from unstructured, ungrammatical data sources on the World Wide Web %U http://dx.doi.org/10.1007/s10032-007-0052-2 %V 10 %X Abstract Information extraction from unstructured, ungrammatical data such as classified listings is difficult because traditional structural and grammatical extraction methods do not apply. Previous work has exploited reference sets to aid such extraction, but it did so using supervised machine learning. In this paper, we present an unsupervised approach that both selects the relevant reference set(s) automatically and then uses it for unsupervised extraction. We validate our approach with experimental results that show our unsupervised extraction is competitive with supervised machine learning approaches, including the previous supervised approach that exploits reference sets.

@article{Michelson2007Unsupervised, abstract = {Abstract Information extraction from unstructured, ungrammatical data such as classified listings is difficult because traditional structural and grammatical extraction methods do not apply. Previous work has exploited reference sets to aid such extraction, but it did so using supervised machine learning. In this paper, we present an unsupervised approach that both selects the relevant reference set(s) automatically and then uses it for unsupervised extraction. We validate our approach with experimental results that show our unsupervised extraction is competitive with supervised machine learning approaches, including the previous supervised approach that exploits reference sets.}, added-at = {2008-12-09T03:00:06.000+0100}, author = {Michelson, Matthew and Knoblock, Craig}, biburl = {https://www.bibsonomy.org/bibtex/260e09fd321d8c6f9ebc3de398642aed5/jamesh}, citeulike-article-id = {2641210}, doi = {http://dx.doi.org/10.1007/s10032-007-0052-2}, interhash = {7d4578dd0063b1049e7ab0bf297ccad2}, intrahash = {60e09fd321d8c6f9ebc3de398642aed5}, journal = {International Journal on Document Analysis and Recognition}, keywords = {badtext extraction}, month = {December}, number = 3, pages = {211--226}, posted-at = {2008-12-05 04:41:19}, priority = {2}, timestamp = {2008-12-09T09:59:02.000+0100}, title = {Unsupervised information extraction from unstructured, ungrammatical data sources on the World Wide Web}, url = {http://dx.doi.org/10.1007/s10032-007-0052-2}, volume = 10, year = 2007 }