Google Inc.

Andrew William Hogue

Jeffrey C Reynar

David J Vespe

Vinicius J Fortuna

Jonathan T Betz

John J Lee

Michael Gordon

Gabriel Taubman

Daniel Loreto

Alexander P Kehlenbeck

John R Provine

David Bryan Alpert

Ankur Bhargava

Andriy Bihun

Elena Erbiceanu

Daniel Francis Lieuwen

Gregory A Morris

Denis M Lynch

David Petrou

Engin Cinar Sahin

Randolph Gregory Brown

Leonardo A Laroco, Jr

Kevin Lerman

Douglas L T Rohde

Benjamin J Mann

Eyal Carmi

Greg Morris

Robert Joseph Siemborski

Daniel H Harrison

Peter J Weinberger

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a dialog system using user feedback. According to one implementation, a method includes receiving, by a dialog engine and from a computing device, a voice input, determining, by the dialog engine, that the received voice input is classified as feedback to an answer of a question; identifying, by the dialog engine, a predetermined feedback scare associated with the feedback; and adjusting a confidence score associated with the question and the answer based on the predetermined feedback score.

Providing answers to voice queries using user feedback

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a dialog system using user feedback. According to one implementation, a method includes receiving, by a dialog engine and from a computing device, a voice input; determining, by the dialog engine, that the received voice input is classified as feedback to an answer of a question; identifying, by the dialog engine, a predetermined feedback score associated with the feedback; and adjusting a confidence score associated with the question and the answer based on the predetermined feedback score.

Embodiments retrieve a set of search results that have been previously identified as having at least one associated date or location. A timeline or map is displayed that visually represents the distribution of the dates or locations within the results. The timeline is displayed with a histogram graph corresponding to the number of dates in the search results at points along the timeline. The map is displayed with markers at the locations corresponding to the locations in the search results. The user can navigate the result set using the displayed timeline or map.

Displaying search results on a one or two dimensional graph

Training a dialog system using user feedback for answers to questions

A system and method for tagging place names with geographic location coordinates, the place names associated with a collection of objects in a memory of a computer system. The system and method process a text string within an object stored in memory to identify a first potential place name. The system and method determine whether geographic location coordinates are known for the first potential place name. The system and method identify the first potential place name associated with an object in the memory as a place name. The system and method tag the first identified place name associated with an object in the memory with its geographic location coordinates, when the geographic location coordinates for the first identified place name are known. The system and method disambiguate place names when multiple place names are found.

Determining geographic locations for place names

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for query analysis. Queries are identified in query data, and an entity-descriptive portion and a suffix are determined in each query. Query counts are determined for a number of times that the respective queries occur in the query data. Based on the query counts, an entity-level count is estimated, which represents a number of query submissions that include the particular suffix and are considered to refer to a first entity. The entity is determined to be a particular type of entity. A type-level count is determined, which represents a number of query submissions that include the first suffix and are estimated to refer to entities of the particular type of entity. A score is assigned to the particular suffix based on the entity-level count and the type-level count.

Identifying and ranking attributes of entities

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for providing geographically relevant search results. In one aspect, a method includes receiving a geotoken for a resource. The geotoken can be a resource token that references a geographic location. A semantic geotoken can be selected using the received geotoken. The semantic geotoken is a standardized representation of the geographic location that includes one or more location-specific terms. The semantic geotoken is stored with a reference to the resource. Neighboring locations for the geographic location are determined. The neighboring locations are within a predetermined distance of the geographic location. Semantic geotokens for the neighboring locations are selected and stored with the reference to the resource. Data specifying the semantic geotokens and the reference to the resource are provided.

Semantic geotokens

Determining geographic locations for place names in a fact repository

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a dialog system using user feedback. According to one implementation, a method includes receiving, by a dialog engine, a first input that specifies a question; providing, by the dialog engine, an answer to the question; receiving, by the dialog engine, a second input; and determining, by the dialog engine, that the second input is classified as feedback to the answer, then determining a feedback score associated with the second input.

Training a dialog system using user feedback

A presentation engine presents facts in a UI having a graph. Through manipulation of the UI, an end-user can add or remove facts from the graph, and can sort the facts shown in the graph based on values that are shown, or not shown, in the graph. The presentation engine determines a graph type that best facilitates interpretation of the facts by the end-user and automatically creates a graph of that type. Possible graph types include bar graphs, scatter plots, timelines, and maps.

Data object visualization using graphs

Systems and methods for automatic object reference identification and linking in a browseable fact repository database are provided. In some implementations, a method includes, identifying a set of values from a plurality of facts associated with an entity. The plurality of facts are stored in a fact repository, and a respective fact includes: an attribute and a corresponding value. The method further includes, responsive to a search for a first value included in a first fact in the plurality of facts: identifying a second fact associated with the entity; and causing to be displayed to a user: a link associated with the second fact, and information representing a confidence value associated with the second fact. The link, when selected, invokes a search of the fact repository in accordance with one or more search parameters, which include a value corresponding to an attribute included in the second fact.

Automatic object reference identification and linking in a browseable fact repository

Growing community of inventors

Ho Ho Kus, NJ, United States of America

Andrew William Hogue