Google Inc.

John Blitzer

Engin Cinar Sahin

Rahul Gupta

Jakob David Uszkoreit

Jayant Madhavan

Fernando Pereira

Ibrahim Badr

Srinivasan Venkatachary

Matthew K Gray

Dekang Lin

Mahsan Rofouei

Corinn Herrick

Sam Oates

Aditya Shah

Phiroze Parakh

Emma Sarah Persky

Junli Xian

Ciprian Ioan Chelba

Trystan G Upstill

Amarnag Subramanya

Hayden Shaw

Ashish Venugopal

Thomas Richard Strohmann

Ni Lao

Pi-Chuan Chang

Robert B Avery

Edward Everett Anderson

Evgeniy Gabrilovich

Preyas Popat

Shaohua Sun

Aliaksei Severyn

Gaurav Bhaskar Gite

Techniques of generating short answers for queries by a search engine include performing a training operation on a corpus of training data to train the score prediction engine, the corpus of training data including candidate passages providing short answers for display in callouts and remaining respective passages, from which a top scoring short answer is generated. In such implementations, the corpus of training data further includes the remaining respective passages and the respective titles of the candidate passage and remaining respective passages.

Multi source extraction and scoring of short query answers

At least selectively utilizing a large language model (LLM) in generating a natural language (NL) based summary to be rendered in response to a query. In some implementations, in generating the NL based summary additional content is processed using the LLM. The additional content is in addition to query content of the query itself and, in generating the NL based summary, can be processed using the LLM and along with the query content—or even independent of the query content. Processing the additional content can, for example, mitigate occurrences of the NL based summary including inaccuracies and/or can mitigate occurrences of the NL based summary being over-specified and/or under-specified.

Generative summaries for search results

At least selectively utilizing a large language model (LLM) in generating a natural language (NL) based summary to be rendered in response to a query. In some implementations, in generating the NL based summary additional content is processed using the LLM. The additional content is in addition to query content of the query itself and, in generating the NL based summary, can be processed using the LLM and along with the query content&#x2014;or even independent of the query content. Processing the additional content can, for example, mitigate occurrences of the NL based summary including inaccuracies and/or can mitigate occurrences of the NL based summary being over-specified and/or under-specified.

Implementations include systems and methods for querying a data graph. An example method includes receiving a machine learning module trained to produce a model with multiple features for a query, each feature representing a path in a data graph. The method also includes receiving a search query that includes a first search term, mapping the search query to the query, and mapping the first search term to a first entity in the data graph. The method may also include identifying a second entity in the data graph using the first entity and at least one of the multiple weighted features, and providing information relating to the second entity in a response to the search query. Some implementations may also include training the machine learning module by, for example, generating positive and negative training examples from an answer to a query.

Querying a data graph using natural language queries

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for providing a statement that references a particular attribute of a particular topic, in response to providing the statement, obtaining one or more query patterns that each include one or more query terms that are used in queries submitted to a search system in obtaining a value for the particular attribute of the particular topic, generalizing one or more of the query patterns, and associating the one or more generalized query patterns with one or more other topics that include the particular attribute.

Factual query pattern learning

The present disclosure relates to evaluating different semantic interpretations of a search query. One example method includes obtaining a set of search results for a particular search query submitted to a search engine; obtaining a set of semantic interpretations for the particular search query; obtaining, for each semantic interpretation of the set, a canonical search query; generating a modified search query based at least in part on the particular search query and the canonical search query for the semantic interpretation; obtaining a set of search results for the modified search query for the semantic interpretation; and determining, for each semantic interpretation of the set, a degree of similarity between (i) the set of search results of the modified search query for the semantic interpretation, and (ii) the set of search results for the particular search query.

Evaluating semantic interpretations of a search query

Methods and systems are provided for a question answering. In some implementations, a data element to be updated is identified in a knowledge graph and a query is generated based at least in part on the data element. The query is provided to a query processing engine. Information is received from the query processing engine in response to the query. The knowledge graph is updated based at least in part on the received information.

Question answering to populate knowledge base

A language processing system collects similar queries and respective responses and aggregated by responses. Incorrect responses are determined and filtered by the aggregation. The remaining responses are then used to query a high precision system for attributes of entities specified by the queries. The attribute type is determined from the responses of the high precision system, and corresponding parse rules are generated. The parse rules are then associated with an operation that yields a response that specifies an attribute of the attribute type.

Inducing command inputs from high precision and high recall data

A method identifies pairs of first and second command inputs from respective user device sessions for which the first and second operation data are indicative of a first operation failure and a second operation success. The first operation data indicate a first operation performed on data from a first resource property in response to the first command input, and the second operation data indicate a second operation performed on data from a second resource property in response to the second command input. They system determines, from the identified pairs of first and second command inputs, command inputs for which a parsing rule that is associated with the second operation is to be generated.

Inducing command inputs from property sequences

Growing community of inventors

Mountain View, CA, United States of America

John Blitzer