A Survey of Web Information Extraction Systems Export

@article{kayed2006survey, abstract = {The Internet presents a huge amount of useful information which is usually formatted for its users, which makes it difficult to extract relevant data from various sources. Therefore, the availability of robust, flexible Information Extraction (IE) systems that transform the Web pages into program-friendly structures such as a relational database will become a great necessity. Although many approaches for data extraction from Web pages have been developed, there has been limited effort to compare such tools. Unfortunately, in only a few cases can the results generated by distinct tools be directly compared since the addressed extraction tasks are different. This paper surveys the major Web data extraction approaches and compares them in three dimensions: the task domain, the automation degree, and the techniques used. The criteria of the first dimension explain why an IE system fails to handle some Web sites of particular structures. The criteria of the second dimension classify IE systems based on the techniques used. The criteria of the third dimension measure the degree of automation for IE systems. We believe these criteria provide qualitatively measures to evaluate various IE approaches.}, address = {Piscataway, NJ, USA}, author = {Kayed, Mohammed and Shaalan, Khaled F.}, citeulike-article-id = {1179358}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1159162.1159300}, citeulike-linkout-1 = {http://dx.doi.org/10.1109/TKDE.2006.152}, citeulike-linkout-2 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1683775}, doi = {10.1109/TKDE.2006.152}, issn = {1041-4347}, journal = {IEEE Trans. on Knowl. and Data Eng.}, keywords = {language, text}, month = {October}, number = {10}, pages = {1411--1428}, posted-at = {2007-06-08 11:14:52}, priority = {1}, publisher = {IEEE Educational Activities Department}, title = {A Survey of Web Information Extraction Systems}, url = {http://dx.doi.org/10.1109/TKDE.2006.152}, volume = {18}, year = {2006} }

TY - JOUR ID - kayed2006survey L3 - citeulike-article-id:1179358 N2 - The Internet presents a huge amount of useful information which is usually formatted for its users, which makes it difficult to extract relevant data from various sources. Therefore, the availability of robust, flexible Information Extraction (IE) systems that transform the Web pages into program-friendly structures such as a relational database will become a great necessity. Although many approaches for data extraction from Web pages have been developed, there has been limited effort to compare such tools. Unfortunately, in only a few cases can the results generated by distinct tools be directly compared since the addressed extraction tasks are different. This paper surveys the major Web data extraction approaches and compares them in three dimensions: the task domain, the automation degree, and the techniques used. The criteria of the first dimension explain why an IE system fails to handle some Web sites of particular structures. The criteria of the second dimension classify IE systems based on the techniques used. The criteria of the third dimension measure the degree of automation for IE systems. We believe these criteria provide qualitatively measures to evaluate various IE approaches. IS - 10 JF - IEEE Trans. on Knowl. and Data Eng. SN - 1041-4347 AD - Piscataway, NJ, USA EP - 1428 TI - A Survey of Web Information Extraction Systems PB - IEEE Educational Activities Department VL - 18 SP - 1411 KW - language KW - text AU - Kayed, Mohammed AU - Shaalan, Khaled PY - 2006/10// UR - http://dx.doi.org/10.1109/TKDE.2006.152 ER -