公开(公告)号：US20180075343A1

公开(公告)日：2018-03-15

申请号：US15697407

申请日：2017-09-06

Applicant: Google Inc.

Inventor： Aaron Gerard Antonius van den Oord ,  Sander Etienne Lea Dieleman ,  Nal Emmerich Kalchbrenner ,  Karen Simonyan ,  Oriol Vinyals ,  Lasse Espeholt

IPC: G06N3/04 ,  G06F17/27 ,  G10L25/30 ,  G10L15/16 ,  G10L13/08

CPC classification number: G06N3/0472 ,  G06F17/18 ,  G06F17/2765 ,  G06F17/2818 ,  G06N3/0445 ,  G06N3/0454 ,  G06N3/084 ,  G10H2250/311 ,  G10L13/04 ,  G10L13/086 ,  G10L15/16 ,  G10L25/30

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing sequences using convolutional neural networks. One of the methods includes, for each of the time steps: providing a current sequence of audio data as input to a convolutional subnetwork, wherein the current sequence comprises the respective audio sample at each time step that precedes the time step in the output sequence, and wherein the convolutional subnetwork is configured to process the current sequence of audio data to generate an alternative representation for the time step; and providing the alternative representation for the time step as input to an output layer, wherein the output layer is configured to: process the alternative representation to generate an output that defines a score distribution over a plurality of possible audio samples for the time step.

公开(公告)号：US20160358072A1

公开(公告)日：2016-12-08

申请号：US15172074

申请日：2016-06-02

Applicant: Google Inc.

Inventor： Karl Moritz Hermann ,  Tomas Kocisky ,  Edward Thomas Grefenstette ,  Lasse Espeholt ,  William Thomas Kay ,  Mustafa Suleyman ,  Philip Blunsom

IPC: G06N3/08 ,  G06F3/0484

CPC classification number: G06N3/08 ,  G06F3/0484 ,  G06N3/0427 ,  G06N3/0445 ,  G06N3/0454

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for selecting answers to questions about documents. One of the methods includes receiving a document comprising a plurality of document tokens; receiving a question associated with the document, the question comprising a plurality of question tokens; processing the document tokens and the question tokens using a reader neural network to generate a joint numeric representation of the document and the question; and selecting, from the plurality of document tokens, an answer to the question using the joint numeric representation of the document and the question.

Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于选择关于文件的问题的答案。 其中一种方法包括接收包括多个文档令牌的文档; 接收与文档相关联的问题，该问题包括多个问题令牌; 使用读取器神经网络处理文档令牌和问题令牌以生成文档和问题的联合数字表示; 以及使用所述文档和所述问题的联合数字表示从所述多个文档令牌中选择所述问题的答案。

公开(公告)号：US09116780B2

公开(公告)日：2015-08-25

申请号：US13760641

申请日：2013-02-06

Applicant: GOOGLE INC.

Inventor： Jeffrey van Gogh ,  Stephen F. Yegge ,  Michael Joseph Fromberger ,  Amin Shali ,  Gregory Scott West ,  James Anthony Dennett ,  Lasse Espeholt ,  Ronald Aaron Braunstein

IPC: G06F9/44

CPC classification number: G06F8/73 ,  G06F8/75 ,  G06F17/30312

Abstract: A system and method for modeling code segments that do not have a location is disclosed. Source code may be indexed and modeled in a data graph with nodes representing code elements and edges representing relationships between nodes. However, some code elements may be hidden or implicit and therefore may lack location information. In these cases, code figments are created and represented as nodes in the graph. Figment nodes may be specially designated so that the figment nodes may be easily distinguished from real source code nodes. The graph is then updated to include location information for the code figments in the nodes that interact with the hidden or implicit code. The data graph may then be provided to a user or as a service to be used by coding tools.

Abstract translation: 公开了一种用于建模不具有位置的代码段的系统和方法。 源代码可以在数据图中被索引和建模，其中节点表示代表节点之间的关系的代码元素和边。 然而，一些代码元素可能是隐藏的或隐含的，因此可能缺少位置信息。 在这些情况下，创建代码图并将其表示为图中的节点。 图形节点可以被特别指定，使得图形节点可以容易地与实际源代码节点区分开。 然后，该图被更新为包括与隐藏或隐式代码交互的节点中的代码图形的位置信息。 然后可以将数据图形提供给用户或作为编码工具使用的服务。