Processing

Please wait...

Settings

Settings

Goto Application

1. WO2021058266 - DEEP NEURAL ARCHITECTURES FOR DETECTING FALSE CLAIMS

Publication Number WO/2021/058266
Publication Date 01.04.2021
International Application No. PCT/EP2020/074829
International Filing Date 04.09.2020
IPC
G06N 3/04 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architecture, e.g. interconnection topology
G06N 3/08 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
CPC
G06F 40/279
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
40Handling natural language data
20Natural language analysis
279Recognition of textual entities
G06F 40/30
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
40Handling natural language data
30Semantic analysis
G06N 3/0445
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
0445Feedback networks, e.g. hopfield nets, associative networks
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
G06N 3/08
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
Applicants
  • THE UNIVERSITY OF STAVANGER [NO]/[NO]
Inventors
  • SETTY, Vinay
  • MISHRA, Rahul
Agents
  • BRANN AB
Priority Data
16/586,59127.09.2019US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) DEEP NEURAL ARCHITECTURES FOR DETECTING FALSE CLAIMS
(FR) ARCHITECTURES DE NEURONES PROFONDS POUR LA DÉTECTION DE FAUSSES ALLÉGATIONS
Abstract
(EN)
The present disclosure relates to a method and attention neural network for automatically learning embeddings for various latent aspects of textual claims and documents performed in an attention neural network comprising one or more latent aspect models for guiding an attention mechanism of the neural network, wherein the method comprises the steps of inserting a claim document pair, in each of the latent aspect models and a latent aspect vector to select significant sentences to form document representations for each respective latent aspect of the latent aspect vector, concatenating the document representations to establish an overall document representation, calculating a class probability distribution by means of the overall document representation, and classifying the claim of document as true or false using the class probability distribution.
(FR)
La présente divulgation concerne un procédé et un réseau neuronal d'attention pour l'apprentissage automatique de plongements pour divers aspects latents d'allégations textuelles et de documents réalisés dans un réseau neuronal d'attention comprenant un ou plusieurs modèles d'aspect latent pour guider un mécanisme d'attention du réseau neuronal, le procédé comprenant les étapes consistant à insérer une paire de document et d'allégation dans chacun des modèles d'aspect latent et un vecteur d'aspect latent pour sélectionner des phrases significatives afin de former des représentations de documents pour chaque aspect latent respectif du vecteur d'aspect latent, concaténer les représentations de documents pour établir une représentation globale de documents, calculer une distribution de probabilité de classe au moyen de la représentation globale de documents, et classer l'allégation du document comme vraie ou fausse à l'aide de la distribution de probabilité de classe.
Also published as
Latest bibliographic data on file with the International Bureau