G - Physics – 06 – F
Patent
G - Physics
06
F
G06F 17/30 (2006.01)
Patent
CA 2640244
A method and system for propagating the relevance of labeled documents to a query to unlabeled documents is provided. The propagation system provides training data that includes queries, documents labeled with their relevance to the queries, and unlabeled documents. The propagation system then calculates the similarity between pairs of documents in the training data. The propagation system then propagates the relevance of the labeled documents to similar, but unlabeled, documents. The propagation system may iteratively propagate labels of the documents until the labels converge on a solution. The training data with the propagated relevances can then be used to train a ranking function.
L'invention concerne un procédé et un système permettant de propager la pertinence de documents étiquetés à des documents non étiquetés. Le système de propagation fournit des données d'apprentissage qui comportent des interrogations, des documents étiquetés avec leur pertinence aux interrogations, et des documents non étiquetés. Le système de propagation calcule ensuite la similitude entre des paires de documents dans les données d'apprentissage. Le système de propagation propage alors la pertinence des documents étiquetés aux documents similaires, mais non étiquetés. Le système de propagation peut, de manière itérative, propager des étiquettes des documents jusqu'à ce que ces étiquettes convergent sur une solution. Les données d'apprentissage et les pertinences propagées peuvent ensuite servir à former une fonction de classement.
Li Mingjing
Li Zhiwei
Ma Wei-Ying
Wang Jue
Microsoft Corporation
Smart & Biggar
LandOfFree
Propagating relevance from labeled documents to unlabeled... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Propagating relevance from labeled documents to unlabeled..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Propagating relevance from labeled documents to unlabeled... will most certainly appreciate the feedback.
Profile ID: LFCA-PAI-O-1718889