@InProceedings{ Gatterbauer2006:Estimating, author = {Wolfgang Gatterbauer}, title = {Estimating Required Recall for Successful Knowledge Acquisition from the {W}eb}, year = {2006}, month = may # {~23--26,}, booktitle = {Proceedings of the 15th International Conference on {W}orld {W}ide {W}eb ({WWW}~2006)}, pages = {969--970}, location = {Edinburgh, Scotland, UK}, publisher = {ACM Press}, isbn = {1-59593-323-9}, doi = {http://doi.acm.org/10.1145/1135777.1135969}, url = {http://www2006.org/programme/files/xhtml/p209/pp209-gatterbauer.html}, pdf = {http://www2006.org/programme/files/pdf/p209.pdf}, pdf2 = {http://www.dbai.tuwien.ac.at/staff/gatter/work/WWW_2006_Knowledge_Acquisition_from_the_Web.pdf}, abstract = {Information on the Web is not only abundant but also redundant. This redundancy of information has an important consequence on the relation between the recall of an information gathering system and its capacity to harvest the core information of a certain domain of knowledge. This paper provides a new idea for estimating the necessary Web coverage of a knowledge acquisition system in order to achieve a certain desired coverage of the contained core information.}, keyword = {information extraction, quantitative performance measures, recall, redundancy, web metrics}, }