Invention Grant
- Patent Title: Techniques for evaluation, building and/or retraining of a classification model
- Patent Title (中): 评估,建设和/或再培训分类模型的技术
-
Application No.: US13429041Application Date: 2012-03-23
-
Publication No.: US09031897B2Publication Date: 2015-05-12
- Inventor: Etienne Marcheret
- Applicant: Etienne Marcheret
- Applicant Address: US MA Burlington
- Assignee: Nuance Communications, Inc.
- Current Assignee: Nuance Communications, Inc.
- Current Assignee Address: US MA Burlington
- Agency: Wolf, Greenfield & Sacks, P.C.
- Main IPC: G06N99/00
- IPC: G06N99/00 ; G06N7/00

Abstract:
Techniques for evaluation and/or retraining of a classification model built using labeled training data. In some aspects, a classification model having a first set of weights is retrained by using unlabeled input to reweight the labeled training data to have a second set of weights, and by retraining the classification model using the labeled training data weighted according to the second set of weights. In some aspects, a classification model is evaluated by building a similarity model that represents similarities between unlabeled input and the labeled training data and using the similarity model to evaluate the labeled training data to identify a subset of the plurality of items of labeled training data that is more similar to the unlabeled input than a remainder of the labeled training data.
Public/Granted literature
- US20130254153A1 TECHNIQUES FOR EVALUATION, BUILDING AND/OR RETRAINING OF A CLASSIFICATION MODEL Public/Granted day:2013-09-26
Information query