The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Jun. 20, 2017

Filed:

Sep. 10, 2014
Applicant:

Xerox Corporation, Norwalk, CT (US);

Inventors:

Anil Kumar Nelakanti, Meylan, FR;

Guillaume M. Bouchard, Saint Martin le Vinoux, FR;

Cedric Archambeau, Grenoble, FR;

Francis Bach, Paris, FR;

Julien Mairal, La Tronche, FR;

Assignee:

XEROX CORPORATION, Norwalk, CT (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06F 17/20 (2006.01); G06F 17/28 (2006.01); G06F 17/27 (2006.01); G10L 15/197 (2013.01);
U.S. Cl.
CPC ...
G06F 17/28 (2013.01); G06F 17/2775 (2013.01); G10L 15/197 (2013.01);
Abstract

A penalized loss is optimized using a corpus of language samples respective to a set of parameters of a language model. The penalized loss includes a function measuring predictive accuracy of the language model respective to the corpus of language samples and a penalty comprising a tree-structured norm. The trained language model with optimized values for the parameters generated by the optimizing is applied to predict a symbol following sequence of symbols of the language modeled by the language model. In some embodiments the penalty comprises a tree-structured l-norm, such as a tree-structured l-norm or a tree-structured l-norm. In some embodiments a tree-structured l-norm operates on a collapsed suffix trie in which any series of suffixes of increasing lengths which are always observed in the same context are collapsed into a single node. The optimizing may be performed using a proximal step algorithm.


Find Patent Forward Citations

Loading…