%0 Journal Article %1 letham2013growing %A Letham, Benjamin %A Rudin, Cynthia %A Heller, Katherine A. %D 2013 %I Springer US %J Data Mining and Knowledge Discovery %K completion example gazetteer learning list %N 3 %P 372--395 %R 10.1007/s10618-013-0329-7 %T Growing a list %U http://dx.doi.org/10.1007/s10618-013-0329-7 %V 27 %X It is easy to find expert knowledge on the Internet on almost any topic, but obtaining a complete overview of a given topic is not always easy: information can be scattered across many sources and must be aggregated to be useful. We introduce a method for intelligently growing a list of relevant items, starting from a small seed of examples. Our algorithm takes advantage of the wisdom of the crowd, in the sense that there are many experts who post lists of things on the Internet. We use a collection of simple machine learning components to find these experts and aggregate their lists to produce a single complete and meaningful list. We use experiments with gold standards and open-ended experiments without gold standards to show that our method significantly outperforms the state of the art. Our method uses the ranking algorithm Bayesian Sets even when its underlying independence assumption is violated, and we provide a theoretical generalization bound to motivate its use.

@article{letham2013growing, abstract = {It is easy to find expert knowledge on the Internet on almost any topic, but obtaining a complete overview of a given topic is not always easy: information can be scattered across many sources and must be aggregated to be useful. We introduce a method for intelligently growing a list of relevant items, starting from a small seed of examples. Our algorithm takes advantage of the wisdom of the crowd, in the sense that there are many experts who post lists of things on the Internet. We use a collection of simple machine learning components to find these experts and aggregate their lists to produce a single complete and meaningful list. We use experiments with gold standards and open-ended experiments without gold standards to show that our method significantly outperforms the state of the art. Our method uses the ranking algorithm Bayesian Sets even when its underlying independence assumption is violated, and we provide a theoretical generalization bound to motivate its use.}, added-at = {2013-10-24T08:30:41.000+0200}, author = {Letham, Benjamin and Rudin, Cynthia and Heller, Katherine A.}, biburl = {https://www.bibsonomy.org/bibtex/2291de1ac8b7fb3e615aea575556ca68b/jaeschke}, doi = {10.1007/s10618-013-0329-7}, interhash = {1651d6fddd0c9b66208f2af66fe904a8}, intrahash = {291de1ac8b7fb3e615aea575556ca68b}, issn = {1384-5810}, journal = {Data Mining and Knowledge Discovery}, keywords = {completion example gazetteer learning list}, language = {English}, number = 3, pages = {372--395}, publisher = {Springer US}, timestamp = {2014-07-28T15:57:31.000+0200}, title = {Growing a list}, url = {http://dx.doi.org/10.1007/s10618-013-0329-7}, volume = 27, year = 2013 }