Method and system for extracting information from graphs

1. A computer implemented method of mapping a first graphical data structure representation to a second graphical data structure representation, the first graphical data structure representation comprising nodes, with at least one of a plurality of relations between said nodes, the second graphical data structure representation comprising nodes, the mapping comprises using an attention mechanism, wherein said attention mechanism establishes the importance of specific nodes dependent on their neighbourhood and the relations between the nodes, wherein the attention mechanism is enacted by attention coefficients and there is a coupling between attention coefficients across different relations.

2. The method of claim 1 , wherein the attention coefficients across a neighbourhood are normalised.

3. The method of claim 1 , wherein the attention coefficients across a neighbourhood of nodes for one relation are normalised.

4. The method of claim 1 , wherein the nodes of the first graphical data structure representation each comprise a feature vector and the nodes of the second representation also each comprise a feature vector, the mapping converting the features of the feature vectors of the first graphical data structure representation into transformed feature vectors of the second graphical data structure representation.

5. The method of claim 4 , wherein the feature vectors of the first graphical data structure representation are transformed into feature vectors of the second graphical data structure representation via a linear transformation and an attention mechanism.

6. The method of claim 5 , wherein the attention mechanism is configured such that after the linear transformation, the relation between the linearly transformed feature vectors are independent of other relations.

7. The method of claim 6 , wherein the attention mechanism comprises attention coefficients derived from a product of a relation dependent vector with a concatenation of two related nodes where the feature vectors from the two related nodes have been transformed via said linear transformation.

8. The method of claim 7 , wherein the attention coefficients are derived from the said product using an activation function that allows normalisation over the neighbourhood of nodes.

9. The method of claim 5 , wherein matrices that define the linear transformation and the attention mechanism are decomposed.

10. The method of claim 1 , where the attention mechanism is a multi-head attention mechanism.

11. A natural language processing method, adapted to map an input phrase into a form more suitable for a query, the method comprising:

converting the input phrase into a first graphical data structure representation, wherein the words of the input phrase are converted into feature vectors and the semantic relationships between the words provide a plurality of relations between the feature vectors;

mapping said first graphical data structure representation into a second graphical data structure representation wherein the mapping comprises using an attention mechanism, said attention mechanism establishes the importance of specific feature vectors dependent on their neighbourhood and the relations between the feature vectors.

12. A computer implemented classification method, for classifying entities, said entities being defined by feature vectors and having relations between the entities, the method comprising:

representing the feature vectors and relations as a first graphical data structure representation,

mapping said first graphical data structure representation into a second graphical data structure representation wherein the mapping comprises using an attention mechanism, said attention mechanism establishes the importance of specific feature vectors dependent on their neighbourhood and the relations between the feature vectors, said mapping transforming the feature vectors of the first graphical data structure representation to transformed feature vectors in the second graphical data structure representation wherein the transformed feature vectors of said second graphical data structure representation represent classes.

13. A system for mapping a first graphical data structure representation to a second graphical data structure representation, the system comprising a processor and a memory, the processor being configured to:

receive a first graphical data structure representation comprising nodes, with at least one of a plurality of relations between said nodes,

retrieve from memory a pre-trained model adapted to map said first graphical data structure representation to a second graphical data structure representation, wherein the pre-trained model uses an attention mechanism, wherein said attention mechanism establishes the importance of specific nodes dependent on their neighbourhood and the relations between the nodes; and

map the first graphical data structure representation to a the second graphical data structure representation.

14. The system of claim 13 , wherein the first processor comprises a GPU.