Methods, apparatus and products for semantic processing of text

Abstract

The invention relates to a computer-implemented method of training a neural network, comprising: training a first neural network (4) of a self organizing map type with a first set (2) of first text documents (3) each containing one or more keywords (7) in a semantic context to map each document (3) to a point (X i / Y j ) in the self organizing map (5) by semantic clustering; determining, for each keyword (7) occurring in the first set (2), all points (X i / Y j ) in the self organizing map (5) to which first documents (3) containing said keyword (7) are mapped, as a pattern (6) and storing said pattern (6) for said keyword (7) in a pattern dictionary (9); forming at least one sequence (11) of keywords (7) from a second set (12) of second text documents (13) each containing one or more keywords (7) in a semantic context; translating said at least one sequence (11) of keywords (7) into at least one sequence (14) of patterns (6) by using said pattern dictionary (9); and training a second neural network (15) with said at least one sequence (14) of patterns (6). The invention further relates to computer-readable media and classification, prediction and translation machines based on neural networks.

Description

technical field [0001] The invention relates to a neural network training method, especially a method for semantic processing, classification and prediction of text. The invention further relates to computer readable media and neural network based classifiers, predictors and translators. Background technique [0002] In the context of this disclosure, the term "neural network" refers to a computer-implemented, artificial neural network. In e.g. "Neural Networks for Pattern Recognition (Neural Networks for Pattern Recognition)" by Bishop C.M., Oxford University Press, New York, 1995 / 2010; or Hofgray, Bern, 2011 The theory of neural networks is given in Rey, G.D. (Rey G.D.), Wender K.F. (Wendel K.F.) "Neurale Netze (Neural Networks)" by Hans Huber (Hans Huber) 2nd Edition , an overview of types and implementation details. [0003] In particular, the present invention relates to the semantic processing of text by neural networks, ie the analysis of the meaning of a text by f...

AI Technical Summary

Problems solved by technology

[0008] While neural networks are currently widely used for pattern recognition in large amounts of numerical data, their application to text processing is currently limited by the form in which text can be fed to neural networks in machine-readable form

Images