Google Inc.

Engin Cinar Sahin

Emma Sarah Persky

John Blitzer

Vinicius J Fortuna

Jakob David Uszkoreit

Fernando Pereira

Dekang Lin

Rahul Gupta

Junli Xian

Max Bogue

Angela Ni-Hwey Chang

Konrad Piotr Delong

Ciprian Ioan Chelba

Andrew William Hogue

Ian MacGillivray

John R Provine

David Allen Smith

Richard Wang

Kevin Lerman

George Andrei Mihaila

John J Lee

Chen Sun

Daniel Walevski

Daniel Loreto

Daniel A Rocha

Daniel A De M Rocha

Ian Macgillivray

Haran Talmon

Atanas Frengov

A server receives a query identifying one or more attributes of an entity. The server accesses a set of candidate templates for answering the query based on the one or more attributes of the entity, each candidate template having one or more fields, wherein each field is associated with at least one constraint. The server obtains a set of information that answers the query and selects a template from the set of candidate templates, where the selected template has a maximum number of fields with constraints that are satisfied by the set of information. The server then generates a phrase by adding the set of information to the one or more fields of the selected template, such that the phrase comprises an answer to the query. Finally, the server communicates the phrase to a client device.

Generating query answers

Computer-implemented systems and methods are provided for analyzing and responding to a query from a user. Consistent with certain embodiments, systems and methods are provided for receiving a query from the user and dividing the query into query segments based on a set of grammar rules. Further, systems and methods are provided for selecting a first segment from the query segments, receiving at least one tuple stored in association with the user, selecting a second segment from the at least one tuple. Additionally, systems and methods are provided for receiving information related to the first and second segments, and generating a response to the query based on the received information. In addition, systems and methods are provided for transmitting information to a display device for presenting the response to the user.

Systems and methods for generating responses to 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

A computer-implemented method can include identifying one or more candidate topics from a query. The method can generate, for each candidate topic, a candidate topic-answer pair that includes both the candidate topic and an answer to the query for the candidate topic. The method can obtain search results based on the query, wherein one or more of the search results references an annotated resource. For each candidate topic-answer pair, the method can determine a score for the candidate topic-answer pair for use in determining a response to the query, based on (i) an occurrence of the candidate topic in the annotations of the resources referenced by one or more of the search results, and (ii) an occurrence of the answer in annotations of the resources referenced by the one or more search results, or in the resources referenced by the one or more search results.

Determining question and answer alternatives

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

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for refining search results. In one aspect, a method includes presenting search results that are responsive to a search query on a search engine results page and each search result includes a snippet. The method also include receiving a refinement to the search query through the search engine results page and generating a request to update one or more of the snippets based on the refinement. The method also includes receiving one or more updated snippets in response to the request and updating one or more of the search results presented on the search engine results page using the one or more updated snippets.

Refining search results

Systems and methods identify recent or ephemeral events involving entities that can be used to update a data graph or provide enhanced search results. For example, a computer-implemented method includes determining at least one search term for an entity in a data graph and determining a time period having an increase in queries for the at least one search term, the increase meeting a threshold. The method may include determining documents having dates associated with the time period, the documents being responsive to the at least one search term, and analyzing the documents to determine a subject, verb, object triple, where the search term corresponds to the subject or the object of the triple. The method may also include providing an update for the data graph based on the triple. The method may also include generating text describing the triple for inclusion in a search result for the search query.

Discovering entity actions for an entity graph

Growing community of inventors

New York, NY, United States of America

Engin Cinar Sahin