Automating the extraction of data from HTML tables with unknown structure Export

@article{citeulike:1766076, abstract = {Data on the Web in HTML tables is mostly structured, but we usually do not know the structure in advance. Thus, we cannot directly query for data of interest. We propose a solution to this problem based on document-independent extraction ontologies. Our solution entails elements of table understanding, data integration, and wrapper creation. Table understanding allows us to find tables of interest within a Web page, recognize attributes and values within the table, pair attributes with values, and form records. Data-integration techniques allow us to match source records with a target schema. Ontologically specified wrappers allow us to extract data from source records into a target schema. Experimental results show that we can successfully locate data of interest in tables and map the data from source HTML tables with unknown structure to a given target database schema. We can thus ” directly” query source data with unknown structure through a known target schema.}, address = {Amsterdam, The Netherlands, The Netherlands}, author = {Embley, David W. and Tao, Cui and Liddle, Stephen W.}, citeulike-article-id = {1766076}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1077719}, citeulike-linkout-1 = {http://dx.doi.org/10.1016/j.datak.2004.10.004}, citeulike-linkout-2 = {http://www.deg.byu.edu/papers/dke2003etl.pdf}, doi = {10.1016/j.datak.2004.10.004}, journal = {Data Knowl. Eng.}, keywords = {2005, automatic, extraction, ontology}, month = {July}, number = {1}, pages = {3--28}, posted-at = {2007-10-14 03:40:35}, priority = {3}, publisher = {Elsevier Science Publishers B. V.}, title = {Automating the extraction of data from HTML tables with unknown structure}, url = {http://dx.doi.org/10.1016/j.datak.2004.10.004}, volume = {54}, year = {2005} }

TY - JOUR ID - citeulike:1766076 L3 - citeulike-article-id:1766076 N2 - Data on the Web in HTML tables is mostly structured, but we usually do not know the structure in advance. Thus, we cannot directly query for data of interest. We propose a solution to this problem based on document-independent extraction ontologies. Our solution entails elements of table understanding, data integration, and wrapper creation. Table understanding allows us to find tables of interest within a Web page, recognize attributes and values within the table, pair attributes with values, and form records. Data-integration techniques allow us to match source records with a target schema. Ontologically specified wrappers allow us to extract data from source records into a target schema. Experimental results show that we can successfully locate data of interest in tables and map the data from source HTML tables with unknown structure to a given target database schema. We can thus “directly” query source data with unknown structure through a known target schema. IS - 1 JF - Data Knowl. Eng. AD - Amsterdam, The Netherlands, The Netherlands EP - 28 TI - Automating the extraction of data from HTML tables with unknown structure PB - Elsevier Science Publishers B. V. VL - 54 SP - 3 KW - 2005 KW - automatic KW - extraction KW - ontology AU - Embley, David AU - Tao, Cui AU - Liddle, Stephen PY - 2005/07// UR - http://dx.doi.org/10.1016/j.datak.2004.10.004 ER -