Google Inc.

Amarnag Subramanya

Edgar Gonzalez Pellicer

Fernando Pereira

Shalini Agarwal

Vladimir Vuskovic

Melvin Jose Johnson Premkumar

James Kuczmarski

Vibhor Jain

Nimesh Ranjan

Luna Dai

Nihal Sandeep Balani

Jinna Lei

Mengmeng Niu

Rodrigo Lima Carceroni

Daisuke Ikeda

Wangqing Yuan

John Blitzer

Evgeniy Gabrilovich

Pannag Raghunath Sanketi

Rahul Gupta

Wei Lwun Lu

Ni Lao

Eugene Agichtein

Hongjie Chai

Jeffrey Jon Dalton

Jennifer Ann Gillenwater

Fernando Carlos Das Neves Pereira

Denis Savenkov

Kai Chen

Jay Michael Ponte

Hrishikesh Balkrishna Aradhye

Douglas Eck

Wei Hua

Hui Fang

Dipanjan Das

Slav Petrov

Rami Al-Rfou′

Isabelle L Stanton

Michael Ringgaard

Garth Griffin

Daniel Gillick

Miriam King Connor

Jingyi Liu

Dave Orr

Vicente Ignacio Ordonez Roman

Rajhans Samdani

Techniques described herein relate to facilitating end-to-end multilingual communications with automated assistants. In various implementations, speech recognition output may be generated based on voice input in a first language. A first language intent may be identified based on the speech recognition output and fulfilled in order to generate a first natural language output candidate in the first language. At least part of the speech recognition output may be translated to a second language to generate an at least partial translation, which may then be used to identify a second language intent that is fulfilled to generate a second natural language output candidate in the second language. Scores may be determined for the first and second natural language output candidates, and based on the scores, a natural language output may be selected for presentation.

Facilitating communications with automated assistants in multiple languages

Facilitating end-to-end communications with automated assistants in multiple languages

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 computer storage media, for providing app store search results. An example method includes responsive to a first search query directed to an app store: revising the first search query to produce a second search query different from the first search query; obtaining, from an Internet search engine, second search results responsive to the second search query; analyzing the second search results to identify apps available on the app store that are relevant to the second search query; obtaining, from the app store, first search results responsive to the first search query that identify apps available in the app store; and modifying the first search results based on analyzing the second search results.

Providing app store search results

Methods and apparatus are described herein for identifying tasks in messages. In various implementations, natural language processing may be performed on a received message to generate an annotated message. The annotated message may be analyzed pursuant to a grammar. A portion of the message may be classified as a user task entry based on the analysis of the annotated message.

Identifying tasks in messages

Methods, systems, and apparatus for obtaining a resource, identifying a first portion of text of the resource that is characterized as a question, and a second part of text of the resource that is characterized as an answer to the question, identifying an entity that is referenced by one or more terms of the text that is characterized as the question, a relationship type that is referenced by one or more other terms of the text that is characterized as the question, and an entity that is referenced by the text that is characterized as the answer to the question, and adjusting a score for a relationship of the relationship type for the entity that is referenced by the one or more terms of the text that is characterized as the question and the entity that is referenced by the text that is characterized as the answer to the question.

Information extraction from question and answer websites

Methods and apparatus related to associating a segment of an electronic message with one or more segment addressees. One or more message addressees of an electronic message may be identified, the one or more message addressees identifying at least one recipient of the electronic message. A segment of the electronic message may be identified via one or more processors. One or more segment addressees may be determined from the at least one recipient, the one or more segment addressees identifying an addressee for the identified segment. One or more aspects of the segment may be associated with the one or more segment addressees. An indication pertaining to the one or more aspects of the segment may be provided to the one or more segment addressees.

Associating a segment of an electronic message with one or more segment addressees

A method for annotating a message executes at a computing device having one or more processors and memory. The memory stores one or more programs configured for execution by the one or more processors. A plurality of messages for a user is analyzed to determine whether a task reminder is derivable for any of the messages. In this way, task reminders are derived for at least a subset of the messages. A user interface for an electronic messaging application is provided. The interface includes a list of objects, one or more of which represents a collapsed state of a message in the message subset and comprises a summary, task reminder, and a dismissal affordance. Responsive dismissal affordance selection, the task reminder and the dismissal affordances are removed from the object.

Systems and methods for providing suggested reminders

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for classifying documents. One of the methods includes obtaining a collection of training documents, the training documents including positive documents identified as being longform documents and negative documents identified as not being longform documents; extracting one or more features from the training documents, wherein the features represent lexical or textual content of the training documents; and generating a longform document classifier trained using feature instances extracted from the training documents, wherein the generated longform document classifier is trained such that input documents are classified as being longform documents or classified as not being longform documents.

Identifying longform articles

Systems and methods are disclosed for using an additive context model for entity disambiguation. An example method may include receiving a span of text from a document and a phrase vector for the span. The phrase vector may have a quantity of features and represent a context for the span. The method also includes determining a quantity of candidate entities from a knowledge base that have been referred to by the span. For each of the quantity of candidate entities, the method may include determining a support score for the candidate entity for each feature in the phrase vector, combining the support scores additively, and computing a probability that the span resolves to the candidate entity given the context. The method may also include resolving the span to a candidate entity with a highest probability.

Additive context model for entity resolution

Growing community of inventors

Sunnyvale, CA, United States of America

Amarnag Subramanya