公开(公告)号：US09990361B2

公开(公告)日：2018-06-05

申请号：US14878794

申请日：2015-10-08

Applicant: Facebook, Inc.

Inventor： Ying Zhang ,  Fei Huang ,  Xiaolong Wang

IPC: G06F17/28 ,  G06F17/27 ,  G06F17/20 ,  G06F17/21

CPC classification number: G06F17/289 ,  G06F17/271 ,  G06F17/2785 ,  G06F17/2809

Abstract: Snippets can be represented in a language-independent semantic manner. Each portion of a snippet can be represented by a combination of a semantic representation and a syntactic representation, each in its own dimensional space. A snippet can be divided into portions by constructing a dependency structure based on relationships between words and phrases. Leaf nodes of the dependency structure can be assigned: A) a semantic representation according to pre-defined word mappings and B) a syntactic representation according to the grammatical use of the word. A trained semantic model can assign to each non-leaf node of the dependency structure a semantic representation based on a combination of the semantic and syntactic representations of the corresponding lower-level nodes. A trained syntactic model can assign to each non-leaf node a syntactic representation based on a combination of the syntactic representations of the corresponding lower-level nodes and the semantic representation of that node.

公开(公告)号：US10671816B1

公开(公告)日：2020-06-02

申请号：US15968983

申请日：2018-05-02

Applicant: Facebook, Inc.

Inventor： Ying Zhang ,  Fei Huang ,  Xiaolong Wang

IPC: G06F40/58 ,  G06F40/30 ,  G06F40/42 ,  G06F40/211

Abstract: Snippets can be represented in a language-independent semantic manner. Each portion of a snippet can be represented by a combination of a semantic representation and a syntactic representation, each in its own dimensional space. A snippet can be divided into portions by constructing a dependency structure based on relationships between words and phrases. Leaf nodes of the dependency structure can be assigned: A) a semantic representation according to pre-defined word mappings and B) a syntactic representation according to the grammatical use of the word. A trained semantic model can assign to each non-leaf node of the dependency structure a semantic representation based on a combination of the semantic and syntactic representations of the corresponding lower-level nodes. A trained syntactic model can assign to each non-leaf node a syntactic representation based on a combination of the syntactic representations of the corresponding lower-level nodes and the semantic representation of that node.

公开(公告)号：US20190156210A1

公开(公告)日：2019-05-23

申请号：US16192649

申请日：2018-11-15

Applicant: Facebook, Inc.

Inventor： Kaiming He ,  Ross Girshick ,  Xiaolong Wang

IPC: G06N3/08 ,  G06N3/04 ,  G06F17/15 ,  G06F17/30

Abstract: In one embodiment, a method includes training a baseline machine-learning model based on a neural network comprising a plurality of stages, wherein each stage comprises a plurality of neural blocks, accessing a plurality of training samples comprising a plurality of content objects, respectively, determining one or more non-local operations, wherein each non-local operation is based on one or more pairwise functions and one or more unary functions, generating one or more non-local blocks based on the plurality of training samples and the one or more non-local operations, determining a stage from the plurality of stages of the neural network, and training a non-local machine-learning model by inserting each of the one or more non-local blocks in between at least two of the plurality of neural blocks in the determined stage of the neural network.

公开(公告)号：US20170103062A1

公开(公告)日：2017-04-13

申请号：US14878794

申请日：2015-10-08

Applicant: Facebook, Inc.

Inventor： Ying Zhang ,  Fei Huang ,  Xiaolong Wang

IPC: G06F17/28 ,  G06F17/27

CPC classification number: G06F17/289 ,  G06F17/271 ,  G06F17/2785 ,  G06F17/2809

Abstract: Snippets can be represented in a language-independent semantic manner. Each portion of a snippet can be represented by a combination of a semantic representation and a syntactic representation, each in its own dimensional space. A snippet can be divided into portions by constructing a dependency structure based on relationships between words and phrases. Leaf nodes of the dependency structure can be assigned: A) a semantic representation according to pre-defined word mappings and B) a syntactic representation according to the grammatical use of the word. A trained semantic model can assign to each non-leaf node of the dependency structure a semantic representation based on a combination of the semantic and syntactic representations of the corresponding lower-level nodes. A trained syntactic model can assign to each non-leaf node a syntactic representation based on a combination of the syntactic representations of the corresponding lower-level nodes and the semantic representation of that node.