Automatic invocation of a dialog user interface for translation applications

• US 9,195,654 B2
• Filed: 03/15/2013
• Issued: 11/24/2015
• Est. Priority Date: 03/15/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Chechik, Gal, Shynar, Michael, Zomet, Asaf
• Primary Examiner(s): Opsasnick, Michael N
• Application Number:
  US13/834,371
• Publication Number:
  US 20140278346A1
• Time in Patent Office: 984 Days
• Field of Search: 704 1- 10
• US Class Current: 1/1
• CPC Class Codes: G06F 16/353 into predefined classes
• 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

A device is configured to receive a translation query that requests a translation of terms from a source language to a target language; determine translation features associated with the translation query; assign a feature value to each of the translation features to form feature values; apply a feature weight to each of the feature values to generate a final value; and determine whether to provide a dialog translation user interface or a non-dialog translation user interface based on whether the final value satisfies a threshold. The dialog translation user interface may facilitate translation of a conversation, the non-dialog translation user interface may provide translation search results, and the non-dialog translation user interface may be different than the dialog translation user interface. The device also configured to provide the dialog translation user interface for display when the final value satisfies the threshold.

Claims

1. A method comprising:

receiving, by one or more processors of a device, a translation query,

the translation query requesting a translation of one or more terms from a source language to a target language;

determining, by the one or more processors, one or more translation features associated with the translation query;

assigning, by the one or more processors, a feature value to each of the one or more translation features to form one or more feature values;

applying, by the one or more processors, a feature weight to each of the one or more feature values, in a linear or non-linear manner, to generate a final value;

determining, by the one or more processors, whether to provide a dialog translation user interface or a non-dialog translation user interface based on whether the final value satisfies a threshold,

the dialog translation user interface facilitating translation of a conversation,

the non-dialog translation user interface providing;

one or more translation search results, and

one or more links to one or more documents that provide a translation from the source language to the target language, and

the non-dialog translation user interface being different than the dialog translation user interface; and

providing, by the one or more processors, the dialog translation user interface for display when the final value satisfies the threshold.

2. The method of claim 1, further comprising:

providing the non-dialog translation user interface for display when the final value does not satisfy the threshold.

3. The method of claim 1, further comprising:

receiving dialog training data and non-dialog training data;

training a classifier based on the one or more translation features, the dialog training data, and the non-dialog training data;

generating a plurality of feature weights based on the training of the classifier,

the feature weight, applied to each of the one or more feature values, being selected from the plurality of feature weights;

generating a trained classifier based on the plurality of feature weights;

storing the trained classifier; and

receiving the feature weight, applied to each of the one or more feature values, from the trained classifier.

4. The method of claim 1, further comprising:

generating a translation, of the translation query, in the target language associated with the translation query;

providing for display via the dialog translation user interface;

the translation of the translation query in the target language, and

the translation query in the source language;

generating a potential response to the translation query in the target language associated with the translation query; and

providing for display, via the dialog translation user interface, the potential response in the target language.

5. The method of claim 1, further comprising:

receiving an indication that a user approves of the dialog translation user interface; and

altering the threshold based on the indication.

6. The method of claim 1, further comprising:

receiving a request to export information from the dialog translation user interface to a messaging application; and

exporting the information from the dialog translation user interface to the messaging application based on the request.

7. The method of claim 1, further comprising:

providing an option, via the dialog translation user interface, to change the source language or the target language associated with the translation query; and

changing the source language or the target language when the option is selected by the user.

8. The method of claim 1, further comprising:

providing, via the dialog translation user interface, a dialog history in the source language and the target language associated with the translation query.

9. A non-transitory computer-readable medium for storing instructions, the instructions comprising:

one or more instructions that, when executed by one or more processors of a device, cause the one or more processors to;

receive a translation query,

the translation query requesting a translation of one or more terms from a source language to a target language,

determine one or more translation features associated with the translation query,

assign a feature value to each of the one or more translation features to form one or more feature values,

apply a feature weight to each of the one or more feature values, in a linear or non-linear manner, to generate a final value,

determine whether to provide a dialog translation user interface or a non-dialog translation user interface based on whether the final value satisfies a threshold,

the dialog translation user interface facilitating translation of a conversation,

the non-dialog translation user interface providing one or more links to one or more web sites that provide translation information, and

the non-dialog translation user interface being different than the dialog translation user interface,

provide the dialog translation user interface for display when the final value satisfies the threshold, and

provide the non-dialog translation user interface for display when the final value does not satisfy the threshold.

10. The non-transitory computer-readable medium of claim 9, where the instructions further comprise:

one or more instructions that, when executed by the one or more processors, cause the one or more processors to;

generate a translation, of the translation query, in the target language associated with the translation query,

provide for display via the dialog translation user interface;

the translation of the translation query in the target language, and

the translation query in the source language,

generate a potential response to the translation query in the target language associated with the translation query, and

provide for display, via the dialog translation user interface, the potential response in the target language.

11. The non-transitory computer-readable medium of claim 9, where the instructions further comprise:

one or more instructions that, when executed by the one or more processors, cause the one or more processors to;

receive dialog training data and non-dialog training data,

train a classifier based on the one or more translation features, the dialog training data, and the non-dialog training data,

generate a plurality of feature weights based on the training of the classifier,

the feature weight, applied to each of the one or more feature values, being selected from the plurality of feature weights,

generate a trained classifier based on the plurality of feature weights,

store the trained classifier, and

receive the feature weight, applied to each of the one or more feature values, from the trained classifier.

12. The non-transitory computer-readable medium of claim 9, where the instructions further comprise:

one or more instructions that, when executed by the one or more processors, cause the one or more processors to;

receive a request to export information from the dialog translation user interface to a messaging application, and

export the information from the dialog translation user interface to the messaging application based on the request.

13. The non-transitory computer-readable medium of claim 9, where the instructions further comprise:

one or more instructions that, when executed by the one or more processors, cause the one or more processors to;

receive an indication that a user approves of the dialog translation user interface, and

alter the threshold based on the indication.

14. The non-transitory computer-readable medium of claim 9, where the instructions further comprise:

one or more instructions that, when executed by the one or more processors, cause the one or more processors to;

provide an option, via the dialog translation user interface, to change the source language or the target language associated with the translation query, and

change the source language or the target language when the option is selected by the user.

15. The non-transitory computer-readable medium of claim 9, where the instructions further comprise:

one or more instructions that, when executed by the one or more processors, cause the one or more processors to;

provide, via the dialog translation user interface, a dialog history in the source language and the target language associated with the translation query.

16. A device comprising:

one or more processors to;

receive a translation query,

the translation query requesting a translation of one or more terms from a source language to a target language,

determine one or more translation features associated with the translation query,

generate a value based on the one or more translation features,

determine whether to provide a dialog translation user interface or a non-dialog translation user interface based on whether the value satisfies a threshold,

the dialog translation user interface facilitating translation of a conversation,

the non-dialog translation user interface providing one or more links to one or more websites that provide a translation from the source language to the target language, and

the non-dialog translation user interface being different than the dialog translation user interface,

provide the dialog translation user interface for display when the value satisfies the threshold, and

provide the non-dialog translation user interface for display when the value does not satisfy the threshold.

17. The device of claim 16, where the one or more processors are further to:

receive an indication that a user approves of the dialog translation user interface, and

alter the threshold based on the indication.

18. The device of claim 16, where the one or more processors are further to:

receive a request to export information from the dialog translation user interface to a messaging application, and

export the information from the dialog translation user interface to the messaging application based on the request.

19. The device of claim 16, where the one or more processors are further to:

receive dialog training data and non-dialog training data,

train a classifier based on the one or more translation features, the dialog training data, and the non-dialog training data,

generate a plurality of feature weights based on the training of the classifier,

generate a trained classifier based on the plurality of feature weights,

store the trained classifier,

receive a feature weight from the plurality of feature weights of the trained classifier,

assign a feature value to each of the one or more translation features to form one or more feature values, and

apply the feature weight to each of the one or more feature values to generate the value.

20. The device of claim 16, where the one or more processors are further to:

generate a translation, of the translation query, in the target language associated with the translation query,

provide for display via the dialog translation user interface;

the translation of the translation query in the target language, and

the translation query in the source language,

generate a potential response to the translation query in the target language associated with the translation query, and

provide for display, via the dialog translation user interface, the potential response in the target language.