Patent · US Active

Intelligent augmentation of word representation via character shape embeddings in a neural network

US11222177B2 · kind B2 · utility

0Cited by

3References

20Claims

0Family size

Assignee

International Business Machines Corporation · US

Inventors

Stefano Braghin · Dublin, IE
Cennet Oguz · Stuttgart, DE
Killian Levacher · Dublin, IE

Key dates

Filing date	Apr 3, 2020
Grant date	Jan 11, 2022
Priority date	—
Expiry date	Aug 27, 2040

Classification

Technology area (CPC G)Physics
CPC primaryG06N3/092
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Embodiments are provided for intelligent augmentation of word representations in a computing system by a processor. One or more character shape embeddings may be created in an artificial neural network (ANN) by augmenting one or more word representations based on a set of natural language processing (NLP) data, a set of word embedding vectors, and one or more clustering operations. A shape, a category, and a contextual identify of the one or more word representations may be analyzed used in creating the one or more character shape embeddings.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.