Cross border transaction machine translation

1. A computer implemented method comprising:

receiving a query from a client machine for items, in which the query is in a first language;

translating the query into a second language, including optimizing, for ecommerce, a translation of the query from the first language into the second language based at least in part on an ontology;

obtaining a result set of items in the second language that meet the query;

translating the result set into the first language for presentation to the client machine; and

monitoring feedback from the client machine, including observing actions a user of the client machine takes relative to the result set, the actions including the user purchasing a product from the result set and placing a product watch from the result set; and

building the ontology based at least on part of the observed actions such that the ontology reflects language changes over time.

2. The method of claim 1 , the method further comprising building the ontology based on query context and explicit user feedback, including a rating submitted by the user of the client machine, the rating associated with user perception of a relevance of the results of the query.

3. The method of claim 2 wherein the query context comprises information determined by learning semantic relationships between keywords in the query.

4. The method of claim 2 , wherein building the ontology comprises at least one of measuring a number of items in the result set or abstracting information from the feedback and correlating the feedback to ontological information of the result set.

5. The method of claim 1 wherein the query comprises a plurality of queries received over time.

6. One or more computer-readable hardware storage device having embedded therein a set of instructions which, in response to being executed by one or more processors of a computer, causes the computer to execute operations comprising:

receiving a query from a client machine for items, the query in a first language;

translating the query into a second language, including optimizing, for ecommerce, a translation of the query from the first language into the second language based at least in part on an ontology;

obtaining a result set of items in the second language that meet the query;

translating the result set into the first language for presentation to the client machine; and

monitoring feedback from the client machine, including observing actions a user of the client machine takes relative to the result set, the actions including the user purchasing a product from the result set and placing a product watch from the result set; and

building the ontology based at least on part of the observed actions such that the ontology reflects language changes over time.

7. The one or more computer readable hardware storage device of claim 6 , the operations further comprising building the ontology based at least in part on query context and explicit user feedback, including a rating submitted by the user of the client machine, the rating associated with user perception of a relevance of the results of the query.

8. The one or more computer readable hardware storage device of claim 7 wherein the query context comprises information determined from learning semantic relationships between keywords in the query.

9. The one or more computer readable hardware storage device of claim 6 , wherein building the ontology comprises at least one of measuring a number of items in the result set or abstracting information from the feedback and correlating the feedback to ontological information of the result set.

10. The one or more computer readable hardware storage device of claim 6 , wherein the query comprises a plurality of queries received over time.

11. A non-transitory computer-readable medium having encoded therein programing code executable by one or more hardware processors to perform operations comprising:

receiving a query from a client machine for items, the query in a first language;

translating the query into a second language, including optimizing, for ecommerce, a translation of the query from the first language into the second language based at least in part on an ontology;

obtaining a result set of items in the second language that meet the query;

translating the result set into the first language for presentation to the client machine; and

monitoring feedback from the client machine, including observing actions a user of the client machine takes relative to the result set, the actions including the user purchasing a product from the result set and placing a product watch from the result set; and to build the ontology based at least on part of the observed actions such that the ontology reflects language changes over time.

12. The computer-readable medium of claim 11 , the operations further comprising building the ontology based at least in part on the observed actions and further based at least in part on explicit user feedback, including a rating submitted by the user of the client machine, the rating associated with user perception of a relevance of the results of the query.

13. The computer-readable medium of claim 12 , the operations further comprising determining the query context by learning semantic relationships between keywords in the query.

14. The computer-readable medium of claim 11 , the operations further comprising measuring a number of items in the result set or abstract information from the feedback and to correlate the feedback to ontological information of the result set.

15. The computer-readable medium of claim 11 wherein the query comprises a plurality of queries received over time.