%0 Conference Paper %1 Pasca07 %A Pasca, Marius %A Durme, Benjamin Van %A Garera, Nikesh %B CIKM '07: Proceedings of the sixteenth ACM conference on Conference on information and knowledge management %C New York, NY, USA %D 2007 %I ACM %K KnowledgeAcquisition QueryLogAnalysis TextMining %P 485--494 %R http://doi.acm.org/10.1145/1321440.1321510 %T The role of documents vs. queries in extracting class attributes from text %U http://portal.acm.org/citation.cfm?id=1321440.1321510# %X Challenging the implicit reliance on document collections, this paper discusses the pros and cons of using query logs rather than document collections, as self-contained sources of data in textual information extraction. The differences are quantified as part of a large-scale study on extracting prominent attributes or quantifiable properties of classes (e.g., top speed, price and fuel consumption for CarModel) from unstructured text. In a head-to-head qualitative comparison, a lightweight extraction method produces class attributes that are 45% more accurate on average, when acquired from query logs rather than Web documents. %@ 978-1-59593-803-9

@inproceedings{Pasca07, abstract = {Challenging the implicit reliance on document collections, this paper discusses the pros and cons of using query logs rather than document collections, as self-contained sources of data in textual information extraction. The differences are quantified as part of a large-scale study on extracting prominent attributes or quantifiable properties of classes (e.g., top speed, price and fuel consumption for CarModel) from unstructured text. In a head-to-head qualitative comparison, a lightweight extraction method produces class attributes that are 45% more accurate on average, when acquired from query logs rather than Web documents.}, added-at = {2008-04-27T20:30:07.000+0200}, address = {New York, NY, USA}, author = {Pasca, Marius and Durme, Benjamin Van and Garera, Nikesh}, biburl = {https://www.bibsonomy.org/bibtex/2e7efc07f0a928f6112c25ef40c5cbd68/mkroell}, booktitle = {CIKM '07: Proceedings of the sixteenth ACM conference on Conference on information and knowledge management}, doi = {http://doi.acm.org/10.1145/1321440.1321510}, interhash = {9074336a760490673809ee7eaeaa7be3}, intrahash = {e7efc07f0a928f6112c25ef40c5cbd68}, isbn = {978-1-59593-803-9}, keywords = {KnowledgeAcquisition QueryLogAnalysis TextMining}, location = {Lisbon, Portugal}, pages = {485--494}, publisher = {ACM}, timestamp = {2009-08-06T14:51:22.000+0200}, title = {The role of documents vs. queries in extracting class attributes from text}, url = {http://portal.acm.org/citation.cfm?id=1321440.1321510#}, year = 2007 }