-
公开(公告)号：US20180357240A1
公开(公告)日：2018-12-13
申请号：US16002463
申请日：2018-06-07
Applicant: Facebook, Inc.
Inventor： Alexander Holden Miller , Adam Joshua Fisch , Jesse Dean Dodge , Amir-Hossein Karimi , Antoine Bordes , Jason E. Weston
CPC classification number: G06F17/3053 , G06F17/30513 , G06N99/005
Abstract: In one embodiment, a computing system may generate a query vector representation of an input (e.g., a question). The system may generate relevance measures associated with a set of key-value memories based on comparisons between the query vector representation and key vector representations of the keys in the memories. The system may generate an aggregated result based on the relevance measures and value vector representations of the values in the memories. Through an iterative process that iteratively updates the query vector representation used in each iteration, the system may generate a final aggregated result using a final query vector representation. A combined feature representation may be generated based on the final aggregated result and the final query vector representation. The system may select an output (e.g., an answer to the question) in response to the input based on comparisons between the combined feature representation and a set of candidate outputs.
-
公开(公告)号：US10664744B2
公开(公告)日：2020-05-26
申请号：US15472086
申请日：2017-03-28
Applicant: Facebook, Inc.
Inventor： Jason E. Weston , Arthur David Szlam , Robert D. Fergus , Sainbayar Sukhbaatar
IPC: G06N3/04 , G06N3/08 , G06F16/9032 , G06F40/279
Abstract: Embodiments are disclosed for predicting a response (e.g., an answer responding to a question) using an end-to-end memory network model. A computing device according to some embodiments includes embedding matrices to convert knowledge entries and an inquiry into feature vectors including the input vector and memory vectors. The device further execute a hop operation to generate a probability vector based on an input vector and a first set of memory vectors using a continuous weighting function (e.g., softmax), and to generate an output vector as weighted combination of a second set of memory vectors using the elements of the probability vector as weights. The device can repeat the hop operation for multiple times, where the input vector for a hop operation depends on input and output vectors of previous hop operation(s). The device generates a predicted response based on at least the output of the last hop operation.
-
公开(公告)号：US10402750B2
公开(公告)日：2019-09-03
申请号：US14984956
申请日：2015-12-30
Applicant: Facebook, Inc.
Inventor： Jason E. Weston , Keith Adams , Sumit Chopra
Abstract: In one embodiment, a method includes accessing a first set of entities, with which a user has interacted, and a second set of entities in a social-networking system. A first set of vector representations of the first set of entities are determined using a deep-learning model. A target entity is selected from the first set of entities, and the vector representation of the target entity is removed from the first set. The remaining vector representations in the first set are combined to determine a vector representation of the user. A second set of vector representations of the second set of entities are determined using the deep-learning model. Similarity scores are computed between the user and each of the target entity and the entities in the second set of entities. Vector representations of entities in the second set of entities are updated based on the similarity scores using the deep-learning model.
-
公开(公告)号：US10387464B2
公开(公告)日：2019-08-20
申请号：US14949436
申请日：2015-11-23
Applicant: Facebook, Inc.
Inventor： Jason E. Weston , Keith Adams , Sumit Chopra
Abstract: In one embodiment, a method includes receiving text query that includes n-grams. A vector representation of each n-gram is determined using a deep-learning model. A nonlinear combination of the vector representations of the n-grams is determined, and an embedding of the text query is determined based on the nonlinear combination. The embedding of the text query corresponds to a point in an embedding space, and the embedding space includes a plurality of points corresponding to a plurality of label embeddings. Each label embedding is based on a vector representation of a respective label determined using the deep-learning model. Label embeddings are identified as being relevant to the text query by applying a search algorithm to the embedding space. Points corresponding to the identified label embeddings are within a threshold distance of the point corresponding to the embedding of the text query in the embedding space.
-
公开(公告)号：US20190340538A1
公开(公告)日：2019-11-07
申请号：US16512128
申请日：2019-07-15
Applicant: Facebook, Inc.
Inventor： Jason E. Weston , Keith Adams , Sumit Chopra
Abstract: In one embodiment, a method includes retrieving a first vector representation of a first entity, with which a user has interacted, and a second vector representation of a second entity, with which the user has not interacted. The first and second vector representations are determined using an initial deep-learning model. A first similarity score is computed between a vector representation of the user and the first vector representation, and a second similarity score is computed between the vector representation of the user and the second vector representation. The second vector representation is updated if the second similarity score is greater than the first similarity score using the initial deep-learning model. An updated deep-learning model is generated based on the initial deep-learning model and on the updated second vector representation.
-
Patent Agency Ranking
公开(公告)号：US20190332617A1
公开(公告)日：2019-10-31
申请号：US16505521
申请日：2019-07-08
Applicant: Facebook, Inc.
Inventor： Jason E. Weston , Keith Adams , Sumit Chopra
Abstract: In one embodiment, a method includes receiving, from a client system, a text input comprising one or more n-grams, determining, using a deep-learning model, a vector representation of the text input based on the one or more n-grams, determining an embedding of the vector representation of the text input in a d-dimensional embedding space, identifying one or more labels based on, for each of the one or more labels, a respective similarity of an embedding of a vector representation of the label in the embedding space to the embedding of the vector representation of the text input, and sending, to the client system in response to the received text input, instructions for presenting a user interface comprising one or more of the identified labels as suggested labels.
-
公开(公告)号：US20160188592A1
公开(公告)日：2016-06-30
申请号：US14582731
申请日：2014-12-24
Applicant: Facebook, Inc.
Inventor： Robert D. Fergus , Lubomir Bourdev , Emily Lynn Denton , Jason E. Weston
CPC classification number: G06F16/48 , G06F16/41 , G06F16/437 , G06F16/9535 , G06F16/972 , G06K9/00677 , G06N3/0454 , G06Q50/01
Abstract: Systems, methods, and non-transitory computer-readable media can create, in a training phase, a first content item representation of a first content item based on a first content item transformation. The first content item can comprise one or more of images and video. A first user metadata representation of first user metadata may be created based on a first user metadata transformation. The first content item representation and the first user metadata representation can be combined to produce a first combined representation. The first combined representation and a first tag representation of a first tag can be embedded in an embedding space within a first threshold distance from one another.
Abstract translation: 系统，方法和非暂时计算机可读介质可以在训练阶段中基于第一内容项目变换来创建第一内容项目的第一内容项目表示。 第一内容项目可以包括一个或多个图像和视频。 可以基于第一用户元数据转换来创建第一用户元数据的第一用户元数据表示。 可以组合第一内容项表示和第一用户元数据表示以产生第一组合表示。 可以将第一标签的第一组合表示和第一标签表示嵌入在彼此之间的第一阈值距离内的嵌入空间中。
-
公开(公告)号：US20170061294A1
公开(公告)日：2017-03-02
申请号：US14949436
申请日：2015-11-23
Applicant: Facebook, Inc.
Inventor： Jason E. Weston , Keith Adams , Sumit Chopra
CPC classification number: G06F16/334 , G06F16/3331 , G06N3/0454
Abstract: In one embodiment, a method includes receiving text query that includes n-grams. A vector representation of each n-gram is determined using a deep-learning model. A nonlinear combination of the vector representations of the n-grams is determined, and an embedding of the text query is determined based on the nonlinear combination. The embedding of the text query corresponds to a point in an embedding space, and the embedding space includes a plurality of points corresponding to a plurality of label embeddings. Each label embedding is based on a vector representation of a respective label determined using the deep-learning model. Label embeddings are identified as being relevant to the text query by applying a search algorithm to the embedding space. Points corresponding to the identified label embeddings are within a threshold distance of the point corresponding to the embedding of the text query in the embedding space.
Abstract translation: 在一个实施例中，一种方法包括接收包括n-gram的文本查询。 使用深度学习模型确定每个n-gram的向量表示。 确定n-gram的矢量表示的非线性组合，并且基于非线性组合来确定文本查询的嵌入。 文本查询的嵌入对应于嵌入空间中的一个点，并且嵌入空间包括与多个标签嵌入相对应的多个点。 每个标签嵌入基于使用深度学习模型确定的相应标签的向量表示。 通过将搜索算法应用于嵌入空间，标签嵌入被标识为与文本查询相关。 与识别的标签嵌入相对应的点在与嵌入空间中的文本查询的嵌入相对应的点的阈值距离内。
-
公开(公告)号：US20170277667A1
公开(公告)日：2017-09-28
申请号：US15077814
申请日：2016-03-22
Applicant: Facebook, Inc.
Inventor： Jason E. Weston , Antoine Bordes , Alexandre Lebrun , Martin Jean Raison
IPC: G06F17/24 , G06F17/27 , G06F3/0482
CPC classification number: G06F17/279 , G06F3/0482 , G06F3/0484 , G06F17/30654
Abstract: Techniques to predictively respond to user requests using natural language processing are described. In one embodiment, an apparatus may comprise a client communication component operative to receive a user service request from a user client; an interaction processing component operative to submit the user service request to a memory-based natural language processing component; generate a series of user interaction exchanges with the user client based on output from the memory-based natural language processing component, wherein the series of user interaction exchanges are represented in a memory component of the memory-based natural language processing component; and receive one or more operator instructions for the performance of the user service request from the memory-based natural language processing component; and a user interface component operative to display the one or more operator instructions in an operator console. Other embodiments are described and claimed.
-
公开(公告)号：US20170200077A1
公开(公告)日：2017-07-13
申请号：US15472086
申请日：2017-03-28
Applicant: Facebook, Inc.
Inventor： Jason E. Weston , Arthur David Szlam , Robert D. Fergus , Sainbayar Sukhbaatar
CPC classification number: G06N3/084 , G06F16/90332 , G06F17/2765 , G06N3/0427 , G06N3/0445
Abstract: Embodiments are disclosed for predicting a response (e.g., an answer responding to a question) using an end-to-end memory network model. A computing device according to some embodiments includes embedding matrices to convert knowledge entries and an inquiry into feature vectors including the input vector and memory vectors. The device further execute a hop operation to generate a probability vector based on an input vector and a first set of memory vectors using a continuous weighting function (e.g., softmax), and to generate an output vector as weighted combination of a second set of memory vectors using the elements of the probability vector as weights. The device can repeat the hop operation for multiple times, where the input vector for a hop operation depends on input and output vectors of previous hop operation(s). The device generates a predicted response based on at least the output of the last hop operation.
-
-
-
-
-
-
-
-
-
Search Results
13
records
(took 0.013 seconds)
