Google Inc.

Nuance Communications, Inc.

Brian Strope

Francoise Beaufays

Yun-hsuan Sung

William J Byrne

Olivier Siohan

Quoc V Le

Hy Murveit

Raymond C Kurzweil

Wangqing Yuan

Douglas H Beeferman

Matthew Henderson

Pedro Jose Moreno Mengibar

Fuchun Peng

Trevor D Strohman

Tobias Kaufmann

Kaisuke Nakajima

Mitchel Weintraub

Rami Al-Rfou'

Oriol Vinyals

Larry Paul Heck

Yonghui Wu

Ciprian Ioan Chelba

Gabriel Taubman

Timothy Youngjin Sohn

Balint Miklos

Su-Lin Wu

Xin Lei

Thomas L Dean

Torsten Zeppenfeld

Benjamin N Lee

Howard Scott Roy

Leonid Velikovich

Gregory R Bullock

Ben Shahshahani

Paul Roland Lambert

Jacqueline Amy Tsay

Xu Chen

Matthew Vincent Dierker

Jui-Ting Huang

Hui Lin

Rami Al-Rfou′

Gagan Bansal

Neil Smith

Shalini Ghosh

Victor Anchidin

Noah Constant

Amr Abdelfattah

László Lukacs

Bjarke Ebert

Heeyoung Lee

Matthew Steedman Henderson

Preethi Jyothi

Leif Johnson

Katherine Anna Evans

Cole Austin Bevis

Tobias Bosch

Yinan Wang

Kaushik Roy

Justin Tzi-jay Lu

Do Kook Choe

Ettore Randazzo

Rami Eid Sammouf Al-Rfou'

Jan Van De Kerkhof

Wanqing Yuan

Systems, methods, and computer readable media related to: training an encoder model that can be utilized to determine semantic similarity of a natural language textual string to each of one or more additional natural language textual strings (directly and/or indirectly); and/or using a trained encoder model to determine one or more responsive actions to perform in response to a natural language query. The encoder model is a machine learning model, such as a neural network model. In some implementations of training the encoder model, the encoder model is trained as part of a larger network architecture trained based on one or more tasks that are distinct from a 'semantic textual similarity' task for which the encoder model can be used.

Training encoder model and/or using trained encoder model to determine responsive action(s) for natural language input

Systems, methods, and computer readable media related to information retrieval. Some implementations are related to training and/or using a relevance model for information retrieval. The relevance model includes an input neural network model and a subsequent content neural network model. The input neural network model and the subsequent content neural network model can be separate, but trained and/or used cooperatively. The input neural network model and the subsequent content neural network model can be 'separate' in that separate inputs are applied to the neural network models, and each of the neural network models is used to generate its own feature vector based on its applied input. A comparison of the feature vectors generated based on the separate network models can then be performed, where the comparison indicates relevance of the input applied to the input neural network model to the separate input applied to the subsequent content neural network model.

Cooperatively training and/or using separate input and subsequent content neural networks for information retrieval

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating author vectors. One of the methods includes obtaining a set of sequences of words, the set of sequences of words comprising a plurality of first sequences of words and, for each first sequence of words, a respective second sequence of words that follows the first sequence of words, wherein each first sequence of words and each second sequence of words has been classified as being authored by a first author; and training a neural network system on the first sequences and the second sequences to determine an author vector for the first author, wherein the author vector characterizes the first author.

Generating author vectors

A computing system is described that includes user interface components configured to receive typed user input; and one or more processors. The one or more processors are configured to: receive, by a computing system and at a first time, a first portion of text typed by a user in an electronic message being edited; predict, based on the first portion of text, a first candidate portion of text to follow the first portion of text; output, for display, the predicted first candidate portion of text for optional selection to append to the first portion of text; determine, at a second time that is after the first time, that the electronic message is directed to a sensitive topic; and responsive to determining that the electronic message is directed to a sensitive topic, refrain from outputting subsequent candidate portions of text for optional selection to append to text in the electronic message.

Selective text prediction for electronic messaging

The subject matter of this specification can be embodied in, among other things, a method that includes receiving an audio signal and initiating speech recognition tasks by a plurality of speech recognition systems (SRS's). Each SRS is configured to generate a recognition result specifying possible speech included in the audio signal and a confidence value indicating a confidence in a correctness of the speech result. The method also includes completing a portion of the speech recognition tasks including generating one or more recognition results and one or more confidence values for the one or more recognition results, determining whether the one or more confidence values meets a confidence threshold, aborting a remaining portion of the speech recognition tasks for SRS's that have not generated a recognition result, and outputting a final recognition result based on at least one of the generated one or more speech results.

Speech recognition with parallel recognition tasks

Systems, methods, and computer readable media related to determining one or more responses to provide that are responsive to an electronic communication that is generated through interaction with a client computing device. For example, determining one or more responses to provide for presentation to a user as suggestions for inclusion in a reply to an electronic communication sent to the user. Some implementations are related to training and/or using separate input and response neural network models for determining responses for electronic communications. The input neural network model and the response neural network model can be separate, but trained and/or used cooperatively.

Cooperatively training and/or using separate input and response neural network models for determining response(s) for electronic communications

A method of providing navigation directions includes receiving, at a user terminal, a query spoken by a user, wherein the query spoken by the user includes a speech utterance indicating (i) a category of business, (ii) a name of the business, and (iii) a location at which or near which the business is disposed; identifying, by processing hardware, the business based on the speech utterance; and providing navigation directions to the business via the user terminal.

Personal directory service

A system may use a machine-learned model to determine whether to classify a sequence of one or more words within a first document that is being edited as a candidate hyperlink based at least in part on context associated with the first document. In response to classifying the sequence of one or more words as the candidate hyperlink, the system may use the machine-learned model and based at least in part on the sequence of one or more words and the context to determine one or more candidate document to be hyperlinked from the sequence of one or more words. In response to receiving an indication of a second document being selected out of the one or more candidate documents, the system may modify the first document to associate the sequence of one or more words with a hyperlink to the second document.

Automatic hyperlinking of documents

A method of providing a personal directory service includes receiving, over the Internet, from a user terminal, a query spoken by a user, where the query spoken by the user includes a speech utterance representing a category of persons. The method also includes determining a geographic location of the user terminal, recognizing the category of persons with the speech recognition engine based on the speech utterance representing the category of persons a listing of persons within or near the determined geographic location matching the query to select persons responsive to the query spoken by the user, and sending to the user terminal information related to at least some of the responsive persons.

Growing community of inventors

Palo Alto, CA, United States of America

Brian Strope