Exceptions to action invocation from parsing rules

• US 9,275,034 B1
• Filed: 07/22/2015
• Issued: 03/01/2016
• Est. Priority Date: 06/25/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Uszkoreit, Jakob D., Liang, Percy, Bikel, Daniel M.
• Primary Examiner(s): Pullias, Jesse
• Application Number:
  US14/806,394
• Time in Patent Office: 223 Days
• Field of Search: 704/1, 704/9, 704/10, 704/257, 704270-275
• US Class Current: 1/1
• CPC Class Codes: G06F 16/957 Browsing optimisation, e.g. caching or content distillation
• CPC Class Codes: G06F 40/205 Parsing
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

A language processing system identifies, from log data, command inputs that parsed to a parsing rule associated with an action. If the command input has a signal indicative of user satisfaction, where the signal is derived from data that is not generated from performance of the action (e.g., user interactions with data provided in response to the performance of another, different action; resources identified in response to the performance of another, different action having a high quality score; etc.), then exception data is generated for the parsing rule. The exception data specifies the particular instance of the sentence parsed by the parsing rule, and precludes invocation of the action associated with the rule.

Claims

1. A computer-implemented method performed by a data processing apparatus, the method comprising:

identifying first input sentences that are successfully parsed by a first parsing rule that is associated with a first action;

identifying from among the first input sentences a second input sentence having a signal indicative of user satisfaction, wherein the signal is derived from data that is independent of performance of the first action, the identifying comprising, for each first input sentence;

determining that a second action for which the first input sentence was received as input was performed, the second action being different from the first action;

determining that data responsive to the second action meets a quality threshold;

in response to the data responsive to the second action meeting the quality threshold, determining that the first input sentence is a second input sentence having a signal indicative of user satisfaction; and

generating data that precludes invocation of the first action for the second input sentence.

2. The computer-implemented method of claim 1, wherein the second action is a search operation, and the data responsive to the search operation are resources identified by search results for the search operation.

3. The computer-implemented method of claim 1, wherein the second action is not invoked in response to a successful parse by a parsing rule.

4. The computer-implemented method of claim 1, wherein the input sentences are generated from voice command inputs.

5. The computer-implemented method of claim 1, wherein the parsing rule is a grammar based rule.

6. A non-transitory computer readable storage medium storing instructions executable by a data processing apparatus and that upon such execution causes the data processing apparatus to perform operations comprising:

identifying first input sentences that are successfully parsed by a first parsing rule that is associated with a first action;

identifying from among the first input sentences a second input sentence having a signal indicative of user satisfaction, wherein the signal is derived from data that is independent of performance of the first action, the identifying comprising, for each first input sentence;

determining that a second action for which the first input sentence was received as input was performed, the second action being different from the first action;

determining that data responsive to the second action meets a quality threshold;

in response to the data responsive to the second action meeting the quality threshold, determining that the first input sentence is a second input sentence having a signal indicative of user satisfaction; and

generating data that precludes invocation of the first action for the second input sentence.

7. The non-transitory computer readable storage medium of claim 6, wherein the second action is a search operation, and the data responsive to the search operation are resources identified by search results for the search operation.

8. The non-transitory computer readable storage medium of claim 6, wherein the second action is not invoked in response to a successful parse by a parsing rule.

9. The non-transitory computer readable storage medium of claim 6, wherein the input sentences are generated from voice command inputs.

10. The non-transitory computer readable storage medium of claim 6, wherein the parsing rule is a grammar based rule.

11. A system, comprising:

a data processing apparatus; and

a non-transitory computer readable storage medium in data communication with the data processing apparatus storing instructions executable by the data processing apparatus and that upon such execution causes the data processing apparatus to perform operations comprising;

identifying first input sentences that are successfully parsed by a first parsing rule that is associated with a first action;

identifying from among the first input sentences a second input sentence having a signal indicative of user satisfaction, wherein the signal is derived from data that is independent of performance of the first action, the identifying comprising, for each first input sentence;

determining that a second action for which the first input sentence was received as input was performed, the second action being different from the first action;

determining that data responsive to the second action meets a quality threshold;

in response to the data responsive to the second action meeting the quality threshold, determining that the first input sentence is a second input sentence having a signal indicative of user satisfaction; and

generating data that precludes invocation of the first action for the second input sentence.

12. The system of claim 11, wherein the second action is a search operation, and the data responsive to the search operation are resources identified by search results for the search operation.

13. The system of claim 11, wherein the second action is not invoked in response to a successful parse by a parsing rule.

14. The system of claim 11, wherein the input sentences are generated from voice command inputs.

15. The system of claim 11, wherein the parsing rule is a grammar based rule.