公开(公告)号：US10922609B2

公开(公告)日：2021-02-16

申请号：US15597290

申请日：2017-05-17

Applicant: Facebook, Inc.

Inventor： Aditya Pal ,  Deepayan Chakrabarti ,  Karthik Subbian ,  Anitha Kannan

IPC: G06N3/08 ,  G06F16/901 ,  G06N3/04 ,  G06N5/02 ,  G06N20/10

Abstract: In one embodiment, a system may access a graph data structure that includes nodes and connections between the nodes. Each node may be associated with a user; each connection between two nodes may represent a relationship between the associated users; and each node may be either labeled or unlabeled with respect to a label type. For each labeled node, a label of the label type of that labeled node may be propagated to other nodes through the connections. For each node, the system may store a label distribution information associated with the label type based on the propagated labels reaching the node. The system may train a machine-learning model using the labels and the label distribution information of a set of the labeled nodes. A predicted label for each unlabeled node may be generated using the model and the label distribution information of the unlabeled node.

公开(公告)号：US10803068B2

公开(公告)日：2020-10-13

申请号：US15011221

申请日：2016-01-29

Applicant: Facebook, Inc.

Inventor： Aditya Pal ,  Amaç Herda{hacek over (g)}delen ,  Sourav Chatterji ,  Sumit Taank ,  Deepayan Chakrabarti

IPC: G06F16/9535 ,  G06Q10/10 ,  G06F16/2457 ,  G06Q50/00

Abstract: Systems, methods, and non-transitory computer-readable media can determine one or more respective topics of interest for at least some users of a social networking system. At least some of the topics can be propagated to at least a first user, wherein the propagated topics were determined to be of interest to users that follow the first user in the social networking system. At least one topic from the propagated topics for which the first user is a topical authority is determined.

公开(公告)号：US20180336457A1

公开(公告)日：2018-11-22

申请号：US15597290

申请日：2017-05-17

Applicant: Facebook, Inc.

Inventor： Aditya Pal ,  Deepayan Chakrabarti ,  Karthik Subbian ,  Anitha Kannan

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

Abstract: In one embodiment, a system may access a graph data structure that includes nodes and connections between the nodes. Each node may be associated with a user; each connection between two nodes may represent a relationship between the associated users; and each node may be either labeled or unlabeled with respect to a label type. For each labeled node, a label of the label type of that labeled node may be propagated to other nodes through the connections. For each node, the system may store a label distribution information associated with the label type based on the propagated labels reaching the node. The system may train a machine-learning model using the labels and the label distribution information of a set of the labeled nodes. A predicted label for each unlabeled node may be generated using the model and the label distribution information of the unlabeled node.

公开(公告)号：US10180935B2

公开(公告)日：2019-01-15

申请号：US15422463

申请日：2017-02-02

Applicant: Facebook, Inc.

Inventor： Daniel Matthew Merl ,  Aditya Pal ,  Stanislav Funiak ,  Seyoung Park ,  Fei Huang ,  Amac Herdagdelen

IPC: G06F17/27 ,  G06F17/22

Abstract: A system for identifying language(s) for content items is disclosed. The system can identify different languages for content item words segments by identifying segment languages that maximize a probability across the segments. The probability can be a combination of: an author's likelihood for the language identified for the first word; a combination of transition frequencies for selected languages identified for words, the transition frequencies indicating likelihoods that a transition occurred to the selected language from the previous word's language; and a combination of observation probabilities indicating, for a given word in the content item, a likelihood the given word is in the identified language. For an in-vocabulary word, the observation probabilities can be based on learned probability for that word. For an out-of-vocabulary word, the probability can be computed by breaking the word into overlapping n-grams and computing combined learned probabilities that each n-gram is in the given language.

公开(公告)号：US20170220577A1

公开(公告)日：2017-08-03

申请号：US15011221

申请日：2016-01-29

Applicant: Facebook, Inc.

Inventor： Aditya Pal ,  Amaç Herdagdelen ,  Sourav Chatterji ,  Sumit Taank ,  Deepayan Chakrabarti

IPC: G06F17/30

Abstract: Systems, methods, and non-transitory computer-readable media can determine one or more respective topics of interest for at least some users of a social networking system. At least some of the topics can be propagated to at least a first user, wherein the propagated topics were determined to be of interest to users that follow the first user in the social networking system. At least one topic from the propagated topics for which the first user is a topical authority is determined.

公开(公告)号：US20180189259A1

公开(公告)日：2018-07-05

申请号：US15422463

申请日：2017-02-02

Applicant: Facebook, Inc.

Inventor： Daniel Matthew Merl ,  Aditya Pal ,  Stanislav Funiak ,  Seyoung Park ,  Fei Huang ,  Amac Herdagdelen

IPC: G06F17/27

CPC classification number: G06F17/275 ,  G06F17/2294 ,  G06F17/2775

Abstract: A system for identifying language(s) for content items is disclosed. The system can identify different languages for content item words segments by identifying segment languages that maximize a probability across the segments. The probability can be a combination of: an author's likelihood for the language identified for the first word; a combination of transition frequencies for selected languages identified for words, the transition frequencies indicating likelihoods that a transition occurred to the selected language from the previous word's language; and a combination of observation probabilities indicating, for a given word in the content item, a likelihood the given word is in the identified language. For an in-vocabulary word, the observation probabilities can be based on learned probability for that word. For an out-of-vocabulary word, the probability can be computed by breaking the word into overlapping n-grams and computing combined learned probabilities that each n-gram is in the given language.