Bootstrapping named entity canonicalizers from English using alignment models

• US 9,146,919 B2
• Filed: 03/14/2013
• Issued: 09/29/2015
• Est. Priority Date: 01/16/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Epstein, Mark Edward, Mengibar, Pedro J.
• Primary Examiner(s): Han, Qi
• Application Number:
  US13/830,969
• Publication Number:
  US 20140200876A1
• Time in Patent Office: 929 Days
• Field of Search: 704/2, 704/4, 704/5, 704/8, 704/9, 704/10, 704/257
• US Class Current: 1/1
• CPC Class Codes: G06F 40/295 Named entity recognition
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training recognition canonical representations corresponding to named-entity phrases in a second natural language based on translating a set of allowable expressions with canonical representations from a first natural language, which may be generated by expanding a context-free grammar for the allowable expressions for the first natural language.

Claims

1. A computer-implemented method, the method comprising:

receiving a set of acceptable expressions, each acceptable expression being a string that identifies a value of a variable entity in a first natural language, each acceptable expression being associated with a canonical representation of the value identified by that expression;

performing, a first machine translator that translates expressions from the first natural language to a second natural language, machine translation on each acceptable expression in the first natural language to obtain a translated expression of the acceptable expression in the second natural language;

associating the canonical representation associated with each acceptable expression with the corresponding translated expression in the second natural language;

providing a set of training data for training a second machine translator that translates expressions in the second natural language that each include a respective translated expression to expressions in the second natural language that each include a respective canonical representation, the set of training data comprising the translated expressions and the canonical representations that are associated with the translated expressions; and

using the second machine translator to translate a particular expression that includes a particular translated expression into a particular translated expression that includes a particular canonical representation.

2. The method of claim 1, further comprising:

generating the set of acceptable expressions from a language defined by a context-free grammar by using formation rules of the grammar, each acceptable expression in the set of acceptable expressions being a string defined by the context-free grammar that identifies a particular value of a variable entity in the first natural language; and

associating a canonical representation of the value of the variable entity each acceptable expression identifies with each acceptable expression in the set of acceptable expressions.

3. The method of claim 2, wherein the set of acceptable expressions includes all possible strings that can be generated using the formation rules of the grammar.

4. The method of claim 1, further comprising:

training the second machine translator, using the set of training data, to translate acceptable expressions for a value of the variable entity in the second natural language to corresponding canonical representations.

5. The method of claim 4, wherein the second machine translator receives information about the context of an acceptable expression for a value of the variable entity in the second language to be translated to a corresponding canonical representation and uses the context information to help translate the acceptable expression for the value of the variable entity in the second natural language to a corresponding canonical representation.

6. The method of claim 4, further comprising:

receiving an expression in the second natural language;

using the second machine translator, translating at least a portion of the expression from the second natural language to a canonical representation of the at least a portion of the expression; and

using a third machine translator, translating the canonical representation of the at least a portion of the expression into an equivalent expression in a third natural language.

7. The method of claim 1, wherein the set of acceptable expressions further comprises acceptable expressions that are strings that identify values of a variable entity in a third natural language.

8. A system comprising:

a data processing apparatus; and

a data store storing instructions executable by the data processing apparatus that upon execution by the data processing apparatus cause the data processing apparatus to perform operations comprising;

receiving a set of acceptable expressions, each acceptable expression being a string that identifies a value of a variable entity in a first natural language, each acceptable expression being associated with a canonical representation of the value identified by that expression;

performing, using a first machine translator that translates expressions from the first natural language to a second natural language, machine translation on each acceptable expression in the first natural language to obtain a translated expression of the acceptable expression in the second natural language;

associating the canonical representation associated with each acceptable expression with the corresponding translated expression in the second natural language;

providing a set of training data for training a second machine translator that translates expressions in the second natural language that each include a respective translated expression to expressions in the second natural language that each include a respective canonical representation, the set of training data comprising the translated expressions and the canonical representations that are associated with the translated expressions; and

using the second machine translator to translate a particular expression that includes a particular translated expression into a particular translated expression that includes a particular canonical representation.

9. The system of claim 8, wherein the operations further comprise:

generating the set of acceptable expressions from a language defined by a context-free grammar by using formation rules of the grammar, each acceptable expression in the set of acceptable expressions being a string defined by the context-free grammar that identifies a particular value of a variable entity in the first natural language; and

associating a canonical representation of the value of the variable entity each acceptable expression identifies with each acceptable expression in the set of acceptable expressions.

10. The system of claim 9, wherein the set of acceptable expressions includes all possible strings that can be generated using the formation rules of the grammar.

11. The system of claim 8, wherein the operations further comprise:

training the second machine translator, using the set of training data, to translate acceptable expressions for a value of the variable entity in the second natural language to corresponding canonical representations.

12. The system of claim 11, wherein the second machine translator receives information about the context of an acceptable expression for a value of the variable entity in the second language to be translated to a corresponding canonical representation and uses the context information to help translate the acceptable expression for the value of the variable entity in the second natural language to a corresponding canonical representation.

13. The system of claim 11, wherein the operations further comprise:

receiving an expression in the second natural language;

using the second machine translator, translating at least a portion of the expression from the second natural language to a canonical representation of the at least a portion of the expression; and

using a third machine translator, translating the canonical representation of the at least a portion of the expression into an equivalent expression in a third natural language.

14. The system of claim 8, wherein the set of acceptable expressions further comprises acceptable expressions that are strings that identify values of a variable entity in a third natural language.

15. A non-transitory computer storage medium encoded with a computer program, the program comprising instructions that when executed by a data processing apparatus cause the data processing apparatus to perform operations comprising:

receiving a set of acceptable expressions, each acceptable expression being a string that identifies a value of a variable entity in a first natural language, each acceptable expression being associated with a canonical representation of the value identified by that expression;

performing, sing a first machine translator that translates expressions from the first natural language to a second natural language, machine translation on each acceptable expression in the first natural language to obtain a translated expression of the acceptable expression in the second natural language;

associating the canonical representation associated with each acceptable expression with the corresponding translated expression in the second natural language;

providing a set of training data for training a second machine translator that translates expressions in the second natural language that each include a respective translated expression to expressions in the second natural language that each include a respective canonical representation, the set of training data comprising the translated expressions and the canonical representations that are associated with the translated expressions; and

using the second machine translator to translate a particular expression that includes a particular translated expression into a particular translated expression that includes a particular canonical representation.

16. The computer storage medium of claim 15, wherein the operations further comprise:

generating the set of acceptable expressions from a language defined by a context-free grammar by using formation rules of the grammar, each acceptable expression in the set of acceptable expressions being a string defined by the context-free grammar that identifies a particular value of a variable entity in the first natural language; and

associating a canonical representation of the value of the variable entity each acceptable expression identifies with each acceptable expression in the set of acceptable expressions.

17. The computer storage medium of claim 15, wherein the operations further comprise:

training the second machine translator, using the set of training data, to translate acceptable expressions for a value of the variable entity in the second natural language to corresponding canonical representations.

18. The computer storage medium of claim 17, wherein the second machine translator receives information about the context of an acceptable expression for a value of the variable entity in the second language to be translated to a corresponding canonical representation and uses the context information to help translate the acceptable expression for the value of the variable entity in the second natural language to a corresponding canonical representation.

19. The computer storage medium of claim 17, wherein the operations further comprise:

receiving an expression in the second natural language;

using the second machine translator, translating at least a portion of the expression from the second natural language to a canonical representation of the at least a portion of the expression; and

using a third machine translator, translating the canonical representation of the at least a portion of the expression into an equivalent expression in a third natural language.

20. The computer storage medium of claim 15, wherein the set of acceptable expressions further comprises acceptable expressions that are strings that identify values of a variable entity in a third natural language.