Bibtex de la publication

@InProceedings{ KoPiBo2011.2,
author = {Kopliku, Arlind and Pinel-Sauvagnat, Karen and Boughanem, Mohand},
title = "{Attribute Retrieval from Relational Web tables (regular paper)}",
booktitle = "{Symposium on String Processing and Information Retrieval (SPIRE 2011), Pisa, Italy, 17/10/11-21/10/11}",
year = {2011},
month = {octobre},
publisher = {Springer},
address = {},
pages = {117--128},
language = {anglais},
URL = {},
keywords = {information retrieval, attribute retrieval, SIGRI},
note = {tauxAcceptation: (t=102, l=30, c=10), (t=39.2%, l=29.4%, c=9.8%)},
abstract = {In this paper, we propose an attribute retrieval approach which extracts and ranks attributes from HTML tables. Given an instance (e.g. Tower of Pisa), we want to retrieve from the Web its attributes (e.g. height, architect). Our approach uses HTML tables which are probably the largest source for attribute retrieval. Three recall oriented fi lters are applied over tables to check the following three properties: (i) is the table relational, (ii) has the table a header, and (iii) the conformity of its attributes and values. Candidate attributes are extracted from tables and ranked with a combination of relevance features. Our approach can be applied to all instances and is shown to have a high recall and a reasonable precision. Moreover, it outperforms state of the art techniques.}