Methods, apparatus and products for semantic processing of text

1. A computer-implemented method of training a neural network, comprising:

training a first neural network of a self organizing map type with a first set of first text documents each containing one or more keywords in a semantic context to map each document to a point in the self organizing map by semantic clustering;

performing a reverse indexing by determining, for each keyword occurring in the first set, all points in the self organizing map to which first documents containing said keyword are mapped, and storing said mapped points as a pattern for said keyword in a pattern dictionary;

forming at least one sequence of keywords from a second set of second text documents each containing one or more keywords in a semantic context;

translating said at least one sequence of keywords into at least one sequence of patterns by using said pattern dictionary; and

training a second target neural network with said at least one sequence of patterns.

2. The method of claim 1 , wherein the second neural network is hierarchical and at least partly recurrent.

3. The method of claim 1 , wherein the second neural network is a memory prediction framework.

4. The method of claim 1 , wherein the second neural network is a hierarchical temporal memory.

5. The method of claim 1 , wherein the first neural network is a Kohonen self organizing map.

6. The method of claim 1 , wherein for each of the second documents of the second set a separate sequence of keywords is formed and translated into a separate sequence of patterns and the second neural network is trained successively with each of said separate sequences of patterns.

7. The method of claim 6 , wherein the second documents are sorted by ascending complexity and, when training the second neural network, the separate sequences of patterns are fed into the second neural network in the sorting order of the second documents from which they have each been formed and translated.

8. The method of claim 7 , wherein the complexity of a second document is ascertained on the basis of one or more of: the number of different keywords in that second document, the average length of a sentence in that second document, the frequency of one or more keywords of the first set in that second document, the frequency of one or more keywords of that second document in the first set or another text corpus.

9. The method of claim 1 , comprising:

translating said at least one keyword into at least one pattern by means of the pattern dictionary;

feeding said at least one pattern as an input pattern into said trained second neural network;

obtaining at least one output pattern from said trained second neural network; and

translating said at least output pattern into at least one keyword by means of the pattern dictionary.

10. The method of claim 9 , wherein the second neural network is hierarchical, said at least one input pattern is fed into at least one lower layer of the hierarchy and said at least one output pattern is obtained from at least one higher layer of the hierarchy.

11. The method of claim 10 , wherein the second neural network is at least one of a memory prediction framework or a hierarchical temporal memory.

12. The method of claim 9 , wherein the second neural network is hierarchical, said at least one input pattern is fed into at least one higher layer of the hierarchy and said at least one output pattern is obtained from at least one lower layer of the hierarchy.

13. The method of claim 12 , wherein the second neural network is at least one of a memory prediction framework or a hierarchical temporal memory.

14. A computer-implemented classification machine, comprising a neural network of a hierarchical temporal memory type which has been trained as said second neural network with a method according to claim 1 .

15. A computer-implemented prediction machine, comprising a neural network of a hierarchical temporal memory type which has been trained as said second neural network with a method according to claim 1 .

16. A computer-implemented translation machine, comprising

a classification machine comprising a neural network of a hierarchical temporal memory type which has been trained as said second neural network with a method according to claim 1 using first and second text documents in a first language; and

a prediction machine comprising a neural network of a hierarchial temporal memory type which has been trained as said second neural network with a method according to claim 1 using first and second text documents in a second language;

wherein nodes of the neural network of the classification machine are connected to nodes of the neural network of the prediction machine.