�ݺ�ߣshows by User: disqiu

�ݺ�ߣshows by User: disqiu / http://www.slideshare.net/images/logo.gif �ݺ�ߣshows by User: disqiu / Sun, 01 Sep 2013 05:17:21 GMT �ݺ�ߣShare feed for �ݺ�ߣshows by User: disqiu Wrapper Generation Supervised by a Noisy Crowd /slideshow/wrapper-generation-supervised-by-a-noisy-crowd/25791105 alf-dbcrowd2013-130901051722-phpapp01
We present solutions based on crowdsourcing platforms to support large-scale production of accurate wrappers around data-intensive websites. Our approach is based on supervised wrapper induction algorithms which demand the burden of generating the training data to the workers of a crowdsourcing platform. Workers are paid for answering simple membership queries chosen by the system. We present two algorithms: a single worker algorithm (ALF) and a multiple workers algorithm (ALFRED). Both the algorithms deal with the inherent uncertainty of the responses and use an active learning approach to select the most informative queries. ALFRED estimates the workers’ error rate to decide at runtime how many workers are needed. The experiments that we conducted on real and synthetic data are encouraging: our approach is able to produce accurate wrappers at a low cost, even in presence of workers with a signiﬁcant error rate.]]>
We present solutions based on crowdsourcing platforms to support large-scale production of accurate wrappers around data-intensive websites. Our approach is based on supervised wrapper induction algorithms which demand the burden of generating the training data to the workers of a crowdsourcing platform. Workers are paid for answering simple membership queries chosen by the system. We present two algorithms: a single worker algorithm (ALF) and a multiple workers algorithm (ALFRED). Both the algorithms deal with the inherent uncertainty of the responses and use an active learning approach to select the most informative queries. ALFRED estimates the workers’ error rate to decide at runtime how many workers are needed. The experiments that we conducted on real and synthetic data are encouraging: our approach is able to produce accurate wrappers at a low cost, even in presence of workers with a signiﬁcant error rate.]]> Sun, 01 Sep 2013 05:17:21 GMT /slideshow/wrapper-generation-supervised-by-a-noisy-crowd/25791105 disqiu@slideshare.net(disqiu) Wrapper Generation Supervised by a Noisy Crowd disqiu We present solutions based on crowdsourcing platforms to support large-scale production of accurate wrappers around data-intensive websites. Our approach is based on supervised wrapper induction algorithms which demand the burden of generating the training data to the workers of a crowdsourcing platform. Workers are paid for answering simple membership queries chosen by the system. We present two algorithms: a single worker algorithm (ALF) and a multiple workers algorithm (ALFRED). Both the algorithms deal with the inherent uncertainty of the responses and use an active learning approach to select the most informative queries. ALFRED estimates the workers’ error rate to decide at runtime how many workers are needed. The experiments that we conducted on real and synthetic data are encouraging: our approach is able to produce accurate wrappers at a low cost, even in presence of workers with a signiﬁcant error rate. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/alf-dbcrowd2013-130901051722-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds" /><br> We present solutions based on crowdsourcing platforms to support large-scale production of accurate wrappers around data-intensive websites. Our approach is based on supervised wrapper induction algorithms which demand the burden of generating the training data to the workers of a crowdsourcing platform. Workers are paid for answering simple membership queries chosen by the system. We present two algorithms: a single worker algorithm (ALF) and a multiple workers algorithm (ALFRED). Both the algorithms deal with the inherent uncertainty of the responses and use an active learning approach to select the most informative queries. ALFRED estimates the workers’ error rate to decide at runtime how many workers are needed. The experiments that we conducted on real and synthetic data are encouraging: our approach is able to produce accurate wrappers at a low cost, even in presence of workers with a signiﬁcant error rate.

Wrapper Generation Supervised by a Noisy Crowd from Disheng Qiu

]]> 718 4 https://cdn.slidesharecdn.com/ss_thumbnails/alf-dbcrowd2013-130901051722-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds presentation White http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 ALFRED demo - www2013 /slideshow/alfred-demo-www2013/21686815 alf-www-demo-130522111317-phpapp02
ALFRED: Crowd Assisted Data Extraction]]>
ALFRED: Crowd Assisted Data Extraction]]> Wed, 22 May 2013 11:13:17 GMT /slideshow/alfred-demo-www2013/21686815 disqiu@slideshare.net(disqiu) ALFRED demo - www2013 disqiu ALFRED: Crowd Assisted Data Extraction <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/alf-www-demo-130522111317-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds" /><br> ALFRED: Crowd Assisted Data Extraction

ALFRED demo - www2013 from Disheng Qiu

]]> 978 2 https://cdn.slidesharecdn.com/ss_thumbnails/alf-www-demo-130522111317-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 ALFRED - www2013 /slideshow/alfred-www2013/21686740 alf-www-130522111129-phpapp01
A Framework for Learning Web Wrappers from the Crowd ]]>
A Framework for Learning Web Wrappers from the Crowd ]]> Wed, 22 May 2013 11:11:29 GMT /slideshow/alfred-www2013/21686740 disqiu@slideshare.net(disqiu) ALFRED - www2013 disqiu A Framework for Learning Web Wrappers from the Crowd <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/alf-www-130522111129-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds" /><br> A Framework for Learning Web Wrappers from the Crowd

ALFRED - www2013 from Disheng Qiu

]]> 812 4 https://cdn.slidesharecdn.com/ss_thumbnails/alf-www-130522111129-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 https://cdn.slidesharecdn.com/profile-photo-disqiu-48x48.jpg?cb=1550918671 Spesso si parla troppo e si fa poco .... https://cdn.slidesharecdn.com/ss_thumbnails/alf-dbcrowd2013-130901051722-phpapp01-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/wrapper-generation-supervised-by-a-noisy-crowd/25791105 Wrapper Generation Sup... https://cdn.slidesharecdn.com/ss_thumbnails/alf-www-demo-130522111317-phpapp02-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/alfred-demo-www2013/21686815 ALFRED demo - www2013 https://cdn.slidesharecdn.com/ss_thumbnails/alf-www-130522111129-phpapp01-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/alfred-www2013/21686740 ALFRED - www2013