Traitement en cours

Veuillez attendre...

Paramétrages

Paramétrages

Aller à Demande

1. US20170061294 - Predicting labels using a deep-learning model

Office États-Unis d'Amérique
Numéro de la demande 14949436
Date de la demande 23.11.2015
Numéro de publication 20170061294
Date de publication 02.03.2017
Numéro de délivrance 10387464
Date de délivrance 20.08.2019
Type de publication B2
CIB
G06N 3/04
GPHYSIQUE
06CALCUL; COMPTAGE
NSYSTÈMES DE CALCULATEURS BASÉS SUR DES MODÈLES DE CALCUL SPÉCIFIQUES
3Systèmes de calculateurs basés sur des modèles biologiques
02utilisant des modèles de réseaux neuronaux
04Architecture, p.ex. topologie d'interconnexion
G06F 16/33
GPHYSIQUE
06CALCUL; COMPTAGE
FTRAITEMENT ÉLECTRIQUE DE DONNÉES NUMÉRIQUES
16Recherche d’informations; Structures de bases de données à cet effet; Structures de systèmes de fichiers à cet effet
30de données textuelles non structurées
33Requêtes
CPC
G06F 16/3331
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
16Information retrieval; Database structures therefor; File system structures therefor
30of unstructured textual data
33Querying
3331Query processing
G06F 16/334
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
16Information retrieval; Database structures therefor; File system structures therefor
30of unstructured textual data
33Querying
3331Query processing
334Query execution
G06N 3/0454
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
0454using a combination of multiple neural nets
Déposants Facebook, Inc.
Inventeurs Jason E. Weston
Keith Adams
Sumit Chopra
Mandataires Baker Botts L.L.P.
Titre
(EN) Predicting labels using a deep-learning model
Abrégé
(EN)

In one embodiment, a method includes receiving text query that includes n-grams. A vector representation of each n-gram is determined using a deep-learning model. A nonlinear combination of the vector representations of the n-grams is determined, and an embedding of the text query is determined based on the nonlinear combination. The embedding of the text query corresponds to a point in an embedding space, and the embedding space includes a plurality of points corresponding to a plurality of label embeddings. Each label embedding is based on a vector representation of a respective label determined using the deep-learning model. Label embeddings are identified as being relevant to the text query by applying a search algorithm to the embedding space. Points corresponding to the identified label embeddings are within a threshold distance of the point corresponding to the embedding of the text query in the embedding space.