%0 Conference Paper %1 baroni-etal-2008-cleaneval %A Baroni, Marco %A Chantree, Francis %A Kilgarriff, Adam %A Sharoff, Serge %B Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08) %C Marrakech, Morocco %D 2008 %I European Language Resources Association (ELRA) %K boilerplate clean cleaneval data dataset set %T Cleaneval: a Competition for Cleaning Web Pages %U http://www.lrec-conf.org/proceedings/lrec2008/pdf/162_paper.pdf %X Cleaneval is a shared task and competitive evaluation on the topic of cleaning arbitrary web pages, with the goal of preparing web data for use as a corpus for linguistic and language technology research and development. The first exercise took place in 2007. We describe how it was set up, results, and lessons learnt

@inproceedings{baroni-etal-2008-cleaneval, abstract = {Cleaneval is a shared task and competitive evaluation on the topic of cleaning arbitrary web pages, with the goal of preparing web data for use as a corpus for linguistic and language technology research and development. The first exercise took place in 2007. We describe how it was set up, results, and lessons learnt}, added-at = {2020-12-11T16:17:17.000+0100}, address = {Marrakech, Morocco}, author = {Baroni, Marco and Chantree, Francis and Kilgarriff, Adam and Sharoff, Serge}, biburl = {https://www.bibsonomy.org/bibtex/2b722933f38e54335036eedec7568a48e/parismic}, booktitle = {Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)}, description = {Cleaneval: a Competition for Cleaning Web Pages - ACL Anthology}, interhash = {3635e9cade0cd297f1af6c624241b69c}, intrahash = {b722933f38e54335036eedec7568a48e}, keywords = {boilerplate clean cleaneval data dataset set}, month = may, publisher = {European Language Resources Association (ELRA)}, timestamp = {2020-12-11T16:18:35.000+0100}, title = {{C}leaneval: a Competition for Cleaning Web Pages}, url = {http://www.lrec-conf.org/proceedings/lrec2008/pdf/162_paper.pdf}, year = 2008 }