MACHINE LANGUAGE TRANSLATION WITH TRANSFER MAPPINGS HAVING VARYING CONTEXT

• US 20100223049A1
• Filed: 05/04/2010
• Published: 09/02/2010
• Est. Priority Date: 06/01/2001
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Menezes, Arul A., Richardson, Stephen D.
• Granted Patent: US 8,275,605 B2
• Time in Patent Office: Days
• US Class Current: 704/5
• CPC Class Codes: G06F 40/45 Example-based machine translation; Alignment

Abstract

A computer-implemented machine translation system translates text from a first language to a second language. The system includes a plurality of mappings, each mapping indicative of associating a dependency structure of the first language with a dependency structure of the second language, wherein at least some of the mappings correspond to dependency structures of the first language having varying context with some common elements, and associated dependency structures of the second language to the dependency structures of the first language. A module receives input text in a first language and outputs output text in a second language based on accessing the plurality of mappings.

Claims

1. A computer readable storage media having information and instructions thereon for a computer-implemented machine translation system to translate text from a first language to a second language, the information and instructions comprising:

a plurality of mappings, each mapping indicative of associating a dependency structure of the first language with a dependency structure of the second language, wherein at least some of the mappings correspond to dependency structures of the first language having varying context with some common elements, and associated dependency structures of the second language to the dependency structures of the first language also having varying context with some common elements; and

a module receiving input text in a first language and outputting output text in a second language based on accessing the plurality of mappings.

2. The computer readable storage media of claim 1 wherein the dependency structures of said at least some of the mappings have two common elements in each of the languages.

3. The computer readable storage media of claim 1 wherein the dependency structures of said at least some of the mappings have three common elements in each of the languages.

4. The computer readable storage media of claim 1 wherein the information includes information indicative of a size of each dependency structure of the first language.

5. The computer readable storage media of claim 1 wherein the information includes information indicative of an extent of a complete alignment of the dependency structures of the first language originating from a larger dependency structure.

6. The computer readable storage media of claim 1 wherein the information includes information indicative of a frequency the dependency structure occurred in training data.

7. The computer readable storage media of claim 1 wherein the information includes information indicative of a type of training data.

8. The computer readable storage media of claim 1 wherein the information includes information indicative of an extent of the dependency structures originating from a complete parse of the corresponding training data.

9. The computer readable storage media of claim 1 wherein the information includes information indicative of score related to confidence of alignment of the corresponding dependency structure.

10. The computer readable storage media of claim 1 wherein at least some of the mappings are indicative of corresponding dependency structures having an element that can vary.

11. The computer readable storage media of claim 10 wherein the element comprises an under-specified node indicating a part of speech but no specific lemma.

12. The computer readable storage media of claim 10 wherein the element comprises an under-specified node indicating neither a specified part of speech nor a specific lemma.

13. The computer readable storage media of claim 10 wherein the element comprises an under-specified node indicating at least one specific syntactic or semantic feature but no specific lemma.

14. A machine translation system to translate text from a first language to a second language, comprising:

memory storing a plurality of mappings, each mapping indicative of associating a dependency structure of the first language with a dependency structure of the second language, wherein at least some of the mappings correspond to dependency structures of the first language having varying context with some common elements, and associated dependency structures of the second language to the dependency structures of the first language, and wherein at least some of the mappings are indicative of corresponding dependency structures having an element that can vary;

a processor configured to access the memory, receive input text in a first language and output text in a second language based on accessing the plurality of mappings.

15. The machine translation system of claim 14 wherein the element comprises an under-specified node indicating a part of speech but no specific lemma.

16. The machine translation system of claim 14 wherein the element comprises an under-specified node indicating neither a specified part of speech nor a specific lemma.

17. The machine translation system of claim 14 wherein the element comprises an under-specified node indicating at least one specific syntactic or semantic feature but no specific lemma.

18. A computer implemented method to translate text from a first language to a second language, comprising:

receiving input text in a first language;

using a processor to access a plurality of mappings, each mapping indicative of associating a dependency structure of the first language with a dependency structure of the second language, wherein at least some of the mappings correspond to dependency structures of the first language having varying context with some common elements, and associated dependency structures of the second language to the dependency structures of the first language;

identifying at least one mapping for translating the input text using additional information related to the mappings; and

outputting text in the second language based on using said at least one mapping.

19. The computer implemented method of claim 18 wherein the additional information includes at least one of information indicative of a size of each dependency structure of the first language;

information indicative of an extent of a complete alignment of the dependency structures of the first language originating from a larger dependency structure; and

information indicative of a frequency the dependency structure occurred in training data.

20. The computer implemented method of claim 18 wherein the additional information includes at least one of information indicative of a type of training data;

information indicative of an extent of the dependency structures originating from a complete parse of the corresponding training data; and

information indicative of score related to confidence of alignment of the corresponding dependency structure.