公开(公告)号：US09262406B1

公开(公告)日：2016-02-16

申请号：US14271997

申请日：2014-05-07

Applicant: Google Inc.

Inventor： Dipanjan Das ,  Kuzman Ganchev ,  Jason Weston ,  Karl Moritz Hermann

IPC: G06F17/28 ,  G06F17/27

CPC classification number: G06N5/027 ,  G06F17/2264 ,  G06F17/274 ,  G06F17/2755 ,  G06F17/2785 ,  G06F17/2872 ,  G06F17/289 ,  G06F17/30625 ,  G06F17/30631 ,  G06F17/3089

Abstract: A computer-implemented technique can include receiving, at a server, labeled training data including a plurality of groups of words, each group of words having a predicate word, each word having generic word embeddings. The technique can include extracting, at the server, the plurality of groups of words in a syntactic context of their predicate words. The technique can include concatenating, at the server, the generic word embeddings to create a high dimensional vector space representing features for each word. The technique can include obtaining, at the server, a model having a learned mapping from the high dimensional vector space to a low dimensional vector space and learned embeddings for each possible semantic frame in the low dimensional vector space. The technique can also include outputting, by the server, the model for storage, the model being configured to identify a specific semantic frame for an input.

Abstract translation: 计算机实现的技术可以包括在服务器处接收包括多组单词的标记训练数据，每组单词具有谓词单词，每个单词具有通用单词嵌入。 该技术可以包括在服务器处提取他们的谓词单词的句法语境中的多组单词。 该技术可以包括在服务器处连接通用词嵌入以创建表示每个单词的特征的高维向量空间。 该技术可以包括在服务器处获得具有从高维矢量空间到低维向量空间的学习映射的模型，以及在低维向量空间中为每个可能的语义帧学习嵌入。 该技术还可以包括由服务器输出用于存储的模型，该模型被配置为识别用于输入的特定语义帧。

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：US20160239739A1

公开(公告)日：2016-08-18

申请号：US15008794

申请日：2016-01-28

Applicant: Google Inc.

Inventor： Dipanjan Das ,  Kuzman Ganchev ,  Jason Weston ,  Karl Moritz Hermann

IPC: G06N5/02 ,  G06F17/22 ,  G06F17/28 ,  G06F17/30

CPC classification number: G06N5/027 ,  G06F17/2264 ,  G06F17/274 ,  G06F17/2755 ,  G06F17/2785 ,  G06F17/2872 ,  G06F17/289 ,  G06F17/30625 ,  G06F17/30631 ,  G06F17/3089

Abstract: A computer-implemented technique can include receiving, at a server, labeled training data including a plurality of groups of words, each group of words having a predicate word, each word having generic word embeddings. The technique can include extracting, at the server, the plurality of groups of words in a syntactic context of their predicate words. The technique can include concatenating, at the server, the generic word embeddings to create a high dimensional vector space representing features for each word. The technique can include obtaining, at the server, a model having a learned mapping from the high dimensional vector space to a low dimensional vector space and learned embeddings for each possible semantic frame in the low dimensional vector space. The technique can also include outputting, by the server, the model for storage, the model being configured to identify a specific semantic frame for an input.

Abstract translation: 计算机实现的技术可以包括在服务器处接收包括多组单词的标记训练数据，每组单词具有谓词单词，每个单词具有通用单词嵌入。 该技术可以包括在服务器处提取他们的谓词单词的句法语境中的多组单词。 该技术可以包括在服务器处连接通用词嵌入以创建表示每个单词的特征的高维向量空间。 该技术可以包括在服务器处获得具有从高维矢量空间到低维向量空间的学习映射的模型，以及在低维向量空间中为每个可能的语义帧学习嵌入。 该技术还可以包括由服务器输出用于存储的模型，该模型被配置为识别用于输入的特定语义帧。

公开(公告)号：US20160358071A1

公开(公告)日：2016-12-08

申请号：US15172068

申请日：2016-06-02

Applicant: Google Inc.

Inventor： Edward Thomas Grefenstette ,  Karl Moritz Hermann ,  Mustafa Suleyman ,  Philip Blunsom

IPC: G06N3/08

CPC classification number: G06N3/08 ,  G06N3/0445 ,  G06N3/063 ,  G06N3/082

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for augmenting neural networks with an external memory. One of the methods includes providing an output derived from the neural network output for the time step as a system output for the time step; maintaining a current state of the external memory; determining, from the neural network output for the time step, memory state parameters for the time step; updating the current state of the external memory using the memory state parameters for the time step; reading data from the external memory in accordance with the updated state of the external memory; and combining the data read from the external memory with a system input for the next time step to generate the neural network input for the next time step.

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，用于利用外部存储器增强神经网络。 其中一种方法包括提供从时间步长的神经网络输出得到的输出作为时间步长的系统输出; 保持外部存储器的当前状态; 从时间步长的神经网络输出确定时间步长的存储器状态参数; 使用时间步长的存储器状态参数来更新外部存储器的当前状态; 根据外部存储器的更新状态从外部存储器读取数据; 以及将从外部存储器读取的数据与用于下一时间步长的系统输入组合以生成下一个时间步长的神经网络输入。