Back to results
US 11,379,527 B2Granted
Sibling search queries
AssigneeGoogle Inc.
InventorTomer Shmiel
Life of this patent
Estimating the term…
Abstract
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining a plurality of sibling search queries for an input search query. In one aspect, a method comprises: receiving an input search query that satisfies a context template comprising a sequence of one or more words and a wildcard, wherein a wildcard represents variable data, wherein the input search query satisfies the context template and comprises a target word sequence that corresponds to the wildcard in the context template; and determining a plurality of sibling search queries for the input search query, wherein each sibling search query satisfies the context template and comprises a sibling word sequence that corresponds to the wildcard in the context template.
Claims20
A method performed by one or more data processing apparatus, the method comprising:
- obtaining a given training example for training a machine learning model, wherein:
- the machine learning model is configured to process an input comprising a sequence of words to generate a classification output comprising a respective score for each of multiple classes;
- and
- the given training example comprises:
- (i) a given training input comprising a sequence of words, and (ii) a target output that should be generated by the machine learning model by processing the given training input;
- generating a plurality of new training examples based on the given training example, wherein each new training example comprises:
- (i) a new training input comprising a sequence of words, and (ii) the target output, wherein generating each new training example comprises:
- identifying, from a search query log, a first set of multiple search queries based on the given training input corresponding to the given training example;
- identifying, from the search query log, a second set of multiple search queries based on the new training input corresponding to the new training example;
- determining a sibling score between the given training input and the new training input based on:
- (i) the first set of multiple search queries, and (ii) the second set of multiple search queries;
- and
- determining that the sibling score between the given training input and the new training input satisfies an acceptance criterion;
- and
- training the machine learning model on the plurality of new training examples.
12 more elements
A system comprising:
- one or more computers;
- and
- one or more storage devices communicatively coupled to the one or more computers, wherein the one or more storage devices store instructions that, when executed by the one or more computers, cause the one or more computers to perform operations comprising:
- obtaining a given training example for training a machine learning model, wherein:
- the machine learning model is configured to process an input comprising a sequence of words to generate a classification output comprising a respective score for each of multiple classes;
- and
- the given training example comprises:
- (i) a given training input comprising a sequence of words, and (ii) a target output that should be generated by the machine learning model by processing the given training input;
- generating a plurality of new training examples based on the given training example, wherein each new training example comprises:
- (i) a new training input comprising a sequence of words, and (ii) the target output, wherein generating each new training example comprises:
- identifying, from a search query log, a first set of multiple search queries based on the given training input corresponding to the given training example;
- identifying, from the search query log, a second set of multiple search queries based on the new training input corresponding to the new training example;
- determining a sibling score between the given training input and the new training input based on:
- (i) the first set of multiple search queries, and (ii) the second set of multiple search queries;
- and
- determining that the sibling score between the given training input and the new training input satisfies an acceptance criterion;
- and
- training the machine learning model on the plurality of new training examples.
15 more elements
One or more non-transitory computer storage media storing instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:
- obtaining a given training example for training a machine learning model, wherein:
- the machine learning model is configured to process an input comprising a sequence of words to generate a classification output comprising a respective score for each of multiple classes;
- and
- the given training example comprises:
- (i) a given training input comprising a sequence of words, and (ii) a target output that should be generated by the machine learning model by processing the given training input;
- generating a plurality of new training examples based on the given training example, wherein each new training example comprises:
- (i) a new training input comprising a sequence of words, and (ii) the target output, wherein generating each new training example comprises:
- identifying, from a search query log, a first set of multiple search queries based on the given training input corresponding to the given training example;
- identifying, from the search query log, a second set of multiple search queries based on the new training input corresponding to the new training example;
- determining a sibling score between the given training input and the new training input based on:
- (i) the first set of multiple search queries, and (ii) the second set of multiple search queries;
- and
- determining that the sibling score between the given training input and the new training input satisfies an acceptance criterion;
- and
- training the machine learning model on the plurality of new training examples.
12 more elements
Dependencies are inferred from the claim text.