Rajiv K Jain

US Patent:

20220382975, Dec 1, 2022

Filed:

May 28, 2021

Appl. No.:

17/333892

Inventors:

- San Jose CA, US
Vlad Morariu - Potomac MD, US
Varun Manjunatha - College Park MD, US
Tong Sun - San Ramon CA, US
Rajiv Jain - Vienna VA, US
Peizhao Li - Waltham MA, US
Jason Kuen - Santa Clara CA, US
Handong Zhao - San Jose CA, US

International Classification:

G06F 40/279
G06N 3/04
G06N 3/08
G06F 16/93
G06F 40/30
G06F 40/205

Abstract:

One example method involves operations for a processing device that include receiving, by a machine learning model trained to generate a search result, a search query for a text input. The machine learning model is trained by receiving pre-training data that includes multiple documents. Pre-training the machine learning model by generating, using an encoder, feature embeddings for each of the documents included in the pre-training data. The feature embeddings are generated by applying a masking function to visual and textual features in the documents. Training the machine learning model also includes generating, using the feature embeddings, output features for the documents by concatenating the feature embeddings and applying a non-linear mapping to the feature embeddings. Training the machine learning model further includes applying a linear classifier to the output features. Additionally, operations include generating, for display, a search result using the machine learning model based on the input.

US Patent:

20220318505, Oct 6, 2022

Filed:

Apr 6, 2021

Appl. No.:

17/223166

Inventors:

- San Jose CA, US
Franck Dernoncourt - San Jose CA, US
Quan Tran - San Jose CA, US
Varun Manjunatha - Newton MA, US
Lidan Wang - San Jose CA, US
Rajiv Jain - Vienna VA, US
Doo Soon Kim - San Jose CA, US
Walter Chang - San Jose CA, US

International Classification:

G06F 40/284
G06F 40/211
G06F 40/30
G06F 40/126
G06N 3/04
G06N 3/08

Abstract:

Systems and methods for natural language processing are described. One or more embodiments of the present disclosure receive a document comprising a plurality of words organized into a plurality of sentences, the words comprising an event trigger word and an argument candidate word, generate word representation vectors for the words, generate a plurality of document structures including a semantic structure for the document based on the word representation vectors, a syntax structure representing dependency relationships between the words, and a discourse structure representing discourse information of the document based on the plurality of sentences, generate a relationship representation vector based on the document structures, and predict a relationship between the event trigger word and the argument candidate word based on the relationship representation vector.

US Patent:

20230059367, Feb 23, 2023

Filed:

Aug 9, 2021

Appl. No.:

17/397407

Inventors:

- San Jose CA, US
Tong Sun - San Jose CA, US
Rajiv Jain - Vienna VA, US
Jiuxiang Gu - College Park MD, US
Franck Dernoncourt - Sunnyvale CA, US

International Classification:

G06F 21/62
G06F 40/295
G06N 20/00

Abstract:

The present disclosure relates to systems, methods, and non-transitory computer-readable media that generate a natural language model that provides user-entity differential privacy. For example, in one or more embodiments, the disclosed systems sample sensitive data points from a natural language dataset. Using the sampled sensitive data points, the disclosed systems determine gradient values corresponding to the natural language model. Further, the disclosed systems generate noise for the natural language model. The disclosed systems generate parameters for the natural language model using the gradient values and the noise, facilitating simultaneous protection of the users and sensitive entities associated with the natural language dataset. In some implementations, the disclosed systems generate the natural language model through an iterative process (e.g., by iteratively modifying the parameters).

US Patent:

20230033114, Feb 2, 2023

Filed:

Jul 23, 2021

Appl. No.:

17/384136

Inventors:

- SAN JOSE CA, US
Rajiv Bhawanji Jain - Falls Church VA, US
Nedim Lipka - Campbell CA, US
Vlad Ion Morariu - Potomac MD, US
Franck Dernoncourt - San Jose CA, US
Varun Manjunatha - Newton MA, US

International Classification:

G06F 16/35
G06F 40/169
G06F 40/289
G06N 3/04

Abstract:

Systems and methods for natural language processing are described. One or more embodiments of the present disclosure identify a claim from a document, wherein the claim corresponds to a topic, create a graph comprising a plurality of nodes having a plurality of node types and a plurality of edges having a plurality of edge types, wherein one of the nodes represents the claim, and wherein each of the edges represents a relationship between a corresponding pair of the nodes, encode the claim based on the graph using a graph convolutional network (GCN) to obtain an encoded claim, classify the claim by decoding the encoded claim to obtain a stance label that indicates a stance of the claim towards the topic, and transmit information indicating a viewpoint of the document towards the topic based on the stance label.

US Patent:

20210166013, Jun 3, 2021

Filed:

Dec 3, 2019

Appl. No.:

16/701586

Inventors:

- San Jose CA, US
Rajiv Jain - Vienna VA, US
Curtis Michael Wigington - San Jose CA, US
Brian Lynn Price - Pleasant Grove UT, US
Brian Lafayette Davis - Provo UT, US

Assignee:

ADOBE INC. - San Jose CA

International Classification:

G06K 9/00
G06F 3/0488
G06N 3/04
G06N 3/08
G06K 9/22

Abstract:

Techniques are provided for generating a digital image of simulated handwriting using an encoder-decoder neural network trained on images of natural handwriting samples. The simulated handwriting image can be generated based on a style of a handwriting sample and a variable length coded text input. The style represents visually distinctive characteristics of the handwriting sample, such as the shape, size, slope, and spacing of the letters, characters, or other markings in the handwriting sample. The resulting simulated handwriting image can include the text input rendered in the style of the handwriting sample. The distinctive visual appearance of the letters or words in the simulated handwriting image mimics the visual appearance of the letters or words in the handwriting sample image, whether the letters or words in the simulated handwriting image are the same as in the handwriting sample image or different from those in the handwriting sample image.

US Patent:

20210103695, Apr 8, 2021

Filed:

Nov 24, 2020

Appl. No.:

17/102675

Inventors:

- San Jose CA, US
Rajiv Jain - Vienna VA, US
Nishant Sankaran - Tonawanda NY, US

International Classification:

G06F 40/117
G06N 5/04
G06K 9/62
G06K 9/00

Abstract:

Certain embodiments involve transforming an electronic document into a tagged electronic document. For instance, an electronic document processing application generates a tagged electronic document from an input electronic document. The electronic document processing application accesses one or more feature maps that identify, via a set of object-recognition rules, identified objects in the electronic document. The electronic document processing application also obtains a heat map of the electronic document that represents attributes in a pixel-wise manner. The electronic document processing application computes a tag by applying a fusion deep learning model to the one or more feature maps and the heat map. The electronic document processing application generates the tagged electronic document by applying the tag to the electronic document.

US Patent:

20200175095, Jun 4, 2020

Filed:

Nov 29, 2018

Appl. No.:

16/204918

Inventors:

- San Jose CA, US
Rajiv Jain - Vienna VA, US
Nishant Sankaran - Tonawanda NY, US

International Classification:

G06F 17/21
G06K 9/00
G06K 9/62
G06N 5/04

Abstract:

In some embodiments, a computing system computes tags for an electronic document. The computing system identifies sets of objects for the electronic document by applying a set of object-recognition rules to the electronic document, with each object-recognition rule generating a set of identified objects. The computing system generates feature maps that represent a set of identified objects. The computing system generates a heat map that identifies attributes of the electronic document including object candidates of the electronic document by applying a page-segmentation machine-learning model to the electronic document. The computing system computes a tag by applying a fusion deep learning module to the feature map and the heat map to correlate a document object identified by the feature map with an attribute of the electronic document identified by the heat map. The computing system generates the tagged electronic document by applying the tag to the electronic document.