-
公开(公告)号:US10083169B1
公开(公告)日:2018-09-25
申请号:US15248966
申请日:2016-08-26
Applicant: Google LLC
Inventor: Shalini Ghosh , Oriol Vinyals , Brian Patrick Strope , Howard Scott Roy , Thomas L. Dean , Larry Paul Heck
CPC classification number: G06F17/279 , G06F17/2881 , G06N3/0445 , G06N3/084
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing word sequences using neural networks. One of the methods includes receiving a first sequence of words arranged according to a first order; and for each word in the first sequence, beginning with a first word in the first order: determining a topic vector that is associated with the word; generating a combined input from the word and the topic vector, and processing the combined input through one or more sequence modeling layers to generate a sequence modeling output for the word; and processing one or more of the sequence modeling outputs through an output layer to generate a neural network output for the first sequence of words.
-
公开(公告)号:US10083157B2
公开(公告)日:2018-09-25
申请号:US15229743
申请日:2016-08-05
Applicant: GOOGLE LLC
Inventor: Brian Patrick Strope , Matthew Steedman Henderson
CPC classification number: G06F17/2264 , G06F16/35 , G06F17/24 , G06F17/274 , G06F17/28 , G06N3/0454 , G06N3/08
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for transforming and classifying text based on analysis of training texts from particular authors. One of the methods includes receiving an input text including one or more words and a requested author; generating a vector stream representing the input text based on an encoder language model and including one or more multi-dimensional vectors associated with associated words of the words of the input text and representing a distribution of contexts in which the associated words occurred in a plurality of training texts; and producing an output text representing a particular transformation of the input text based at least in part on a decoder language model, the generated vector stream, and the requested author.
-
公开(公告)号:US11868724B2
公开(公告)日:2024-01-09
申请号:US17654660
申请日:2022-03-14
Applicant: GOOGLE LLC
Inventor: Quoc V. Le , Brian Patrick Strope
IPC: G06F40/289 , G06F16/31 , G06F16/35
CPC classification number: G06F40/289 , G06F16/31 , G06F16/35
Abstract: 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.
-
公开(公告)号:US11275895B1
公开(公告)日:2022-03-15
申请号:US16824216
申请日:2020-03-19
Applicant: Google LLC
Inventor: Brian Patrick Strope , Quoc V. Le
IPC: G06F40/289 , G06F16/35 , G06F16/31
Abstract: 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.
-
公开(公告)号:US10599770B1
公开(公告)日:2020-03-24
申请号:US15991531
申请日:2018-05-29
Applicant: Google LLC
Inventor: Brian Patrick Strope , Quoc V. Le
Abstract: 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.
-
公开(公告)号:US09984062B1
公开(公告)日:2018-05-29
申请号:US15206777
申请日:2016-07-11
Applicant: Google LLC
Inventor: Brian Patrick Strope , Quoc V. Le
CPC classification number: G06F17/2775 , G06F17/30613 , G06F17/30705
Abstract: 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.
-
公开(公告)号:US20220198145A1
公开(公告)日:2022-06-23
申请号:US17654660
申请日:2022-03-14
Applicant: GOOGLE LLC
Inventor: Quoc V. Le , Brian Patrick Strope
IPC: G06F40/289 , G06F16/35 , G06F16/31
Abstract: 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.
-
公开(公告)号:US10148609B2
公开(公告)日:2018-12-04
申请号:US14932233
申请日:2015-11-04
Applicant: Google LLC
Inventor: Brian Patrick Strope , Francoise Beaufays , Hy Murveit
IPC: H04M11/00 , H04L29/12 , H04L12/66 , H04L12/58 , H04M3/42 , H04M1/725 , H04W4/16 , H04W8/18 , H04M1/64
Abstract: In one implementation a computer-implemented method includes generating a group of telephone contacts for a first user, wherein the generating includes identifying a second user as a contact of the first user based upon a determination that the second user has at least a threshold email-based association with the first user; and adding the identified second user to the group of telephone contacts for the first user. The method further includes receiving a first request to connect a first telephone device associated with the first user to a second telephone device associated with the second user. The method also includes identifying a contact identifier of the second telephone device using the generated group of telephone contacts for the first user, and initiating a connection between the first telephone device and the second telephone device using the identified contact identifier.
-
公开(公告)号:US10049672B2
公开(公告)日:2018-08-14
申请号:US15171374
申请日:2016-06-02
Applicant: Google LLC
Inventor: Brian Patrick Strope , Francoise Beaufays , Olivier Siohan
Abstract: 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.
-
-
-
-
-
-
-
-