Adobe, Inc.

Niyati Himanshu Chhaya

Balaji Vasan Srinivasan

Vishwa Vinay

Kushal Chawla

Sopan Khosla

Cedric Huesler

Harsh Jhamtani

Aparna Garimella

Fan Du

Natwar Modani

Niranjan Shivanand Kumbi

Kokil Jaidka

Vinay Aggarwal

Harshit Agrawal

Prabhat Mahapatra

Rizurekh Saha

Ryan A Rossi

Eunyee Koh

Sumit Shekhar

Iftikhar Ahamath Burhanuddin

Tanya Goyal

Anandhavelu N

Ajay Awatramani

Laurie Marie Byrum

Tripti Shukla

Ponnurangam Kumaraguru

Sharmila Reddy Nangi

Bhanu Prakash Reddy Guda

Abhilasha Sancheti

Sreekanth Reddy

Calvin K C Wong

Aanisha Bhattacharyya

Abhinav Bohra

Md Main Uddin Rony

Projjal Chanda

Jaya Singh

Ayudh Saxena

Jeevana Kruthi Karnuthala

Chloe McConnell

Nikaash Puri

Shiv Kumar Saini

Gaurav Verma

Deepak Pai

Nandakishore Kambhatla

Anandhavelu Natarajan

Pranav Ravindra Maneriker

Prakhar Gupta

Moumita Sinha

Paridhi Maheshwari

Shriram Venkatesh Shet Revankar

Srikrishna Karanam

Payal Bajaj

Atanu R Sinha

Kuldeep Kulkarni

Hyman Chung

Meghanath Macha Yadagiri

Saurabh Mahapatra

Anandha Velu Natarajan

Navita Goyal

Sagnik Mukherjee

Sapthotharan Krishnan Nair

Suryateja Bv

Inderjeet Jayakumar Nair

Rishiraj Saha Roy

Lilly Kumari

Praneetha Vaddamanu

Reddy Sreekanth

Niloy Ganguly

Soumya Vadlamannati

Harshit Nyati

Sajal Rustagi

Akangsha Sunil Bedmutha

Akhash Nakkonda Amarnath

R Kaushik

Pradyot Prakash

Adarsh Kumar

Padmanabhan Anandan

Aman Deep Singh

Nihal Jain

Aarushi Agrawal

Elaine Chao

Nikhil Kaushik

Udit Kalani

Snehal Raj

Jay Mundra

Atharv Tyagi

Ananya Ganesh

Ayush Agarwal

Nitin Rathor

Roodram Paneri

Vineet Vinayak Pasupulety

Lakshya Jagadish

Rutuj Jugade

Anirudh Phukan

Dhwanit Agarwal

Paridhi Jain

Pranav Ravindra Manerikar

Embodiments are disclosed for reflowing an infographic image for display in a mobile device using machine learning models. In particular, in one or more embodiments, the method may include receiving a document for display in a user device, the document including an infographic image. The method may further include identifying, using a convolutional neural network, visual components of the infographic image. The method may further include determining, using an encoder-decoder network, an ordered sequence of the identified visual components. A generative adversarial network then generates a modified visual representation of the infographic image based on the identified visual components and the determined ordered sequence of the identified visual components. The modified visual of representation of the infographic image is then presented for display in a viewing pane of a user device in place of the infographic image.

Reflowing infographics for cross-device display

Certain embodiments involve using machine-learning methods to generate a recommendation for sequential content items. A method involves accessing a content item associated with an interaction stage in an online environment. A stage graph, which includes a ratio of interactions, of the content item is generated. An additional content item that includes additional stage-transition content is identified. A sequencing function outcome indicating a portion of the ratio of interactions is determined. A transition probability of receiving an interaction with stage-transition content and an additional interaction with the additional stage-transition content is calculated. A content provider system is caused to provide a recipient device with interactive content that includes the additional content item.

Machine-learning techniques applied to interaction data for determining sequential content and facilitating interactions in online environments

Embodiments are disclosed for a digital design system trained to segment unstructured text into topically coherent segments. The method may include receiving unstructured text, the unstructured text including a sequence of sentences. The disclosed systems and methods further comprise generating, by a neural network, a hierarchically segmented tree structure representing the unstructured text. The tree structure comprises a plurality of tree structure nodes, where a node of the tree structure nodes represents a sentence from the sequence of sentences. The segments and sub-segments of the unstructured text can then be determined based on node data for nodes of the hierarchically segmented tree structure. Using the determined segments and sub-segments of the unstructured text, a modified representation of the unstructured text can be displayed.

Hierarchical segmentation of unstructured text using neural networks

Embodiments are disclosed for multichannel content recommendation. The method may include receiving an input collection comprising a plurality of images. The method may include extracting a set of feature channels from each of the images. The method may include generating, by a trained machine learning model, an intent channel of the input collection from the set of feature channels. The method may include retrieving, from a content library, a plurality of search result images that include a channel that matches the intent channel. The method may include generating a recommended set of images based on the intent channel and the set of feature channels.

Multichannel content recommendation system

Techniques are described that support automated generation of a digital document from digital videos using machine learning. The digital document includes textual components that describe a sequence of entity and action descriptions from the digital video. These techniques are usable to generate a single digital document based on a plurality of digital videos as well as incorporate user-specified constraints in the generation of the digital document.

Automated digital document generation from digital videos

Methods, computer systems, computer-storage media, and graphical user interfaces are provided for facilitating generation and presentation of insights. In one implementation, a set of data is used to generate a data visualization. A candidate insight associated with the data visualization is generated, the candidate insight being generated in text form based on a text template and comprising a descriptive insight, a predictive insight, an investigative, or a prescriptive insight. A set of natural language insights is generated, via a machine learning model. The natural language insights represent the candidate insight in a text style that is different from the text template. A natural language insight having the text style corresponding with a desired text style is selected for presenting the candidate insight and, thereafter, the selected natural language insight and data visualization are providing for display via a graphical user interface.

Facilitating generation and presentation of advanced insights

A content generator system receives a request to generate content for a target entity, and one or more keywords. The content generator system retrieves, for the target entity, a current stage identifier linking the target entity to a current stage within a multi-stage objective. The content generator system generates an input vector including the current stage identifier, a target stage identifier, a token embedding comprising the one or more keywords, and a position embedding for each of the one or more keywords, the target stage identifier associated with a target stage within the multi-stage objective different from the current stage. The content generator system generates output text content for the target entity by applying a generative transformer network to the input vector. The content generator system transmits the output text content to a computing device associated with the target entity.

Content augmentation with machine generated content to meet content gaps during interaction with target entities

Systems and methods for text simplification are described. Embodiments of the present disclosure identify a simplified text that includes original information from a complex text and additional information that is not in the complex text. Embodiments then compute an entailment score for each sentence of the simplified text using a neural network, wherein the entailment score indicates whether the sentence of the simplified text includes information from a sentence of the complex text corresponding to the sentence of the simplified text. Then, embodiments generate a modified text based on the entailment score, the simplified text, and the complex text, wherein the modified text includes the original information and excludes the additional information. Embodiments may then present the modified text to a user via a user interface.

Text simplification with minimal hallucination

A text style transfer system is described that generates different stylized versions of input text by rewriting the input text according to a target style. To do so, the text style transfer system employs a variational autoencoder to derive separate content and style representations for the input text, where the content representation specifies semantic information conveyed by the input text and the style representation specifies one or more style attributes expressed by the input text. The style representation using counterfactual reasoning to identify different transfer strengths for applying the target style to the input text. Each transfer strength represents a minimum change to the input text that achieves a different expression of the target style. The transfer strengths are then used to generate style representation variants, which are each concatenated with the content representation of the input text to generate the plurality of different stylized versions of the input text.

Counterfactual text stylization

A text summarization system auto-generates text summarization models using a combination of neural architecture search and knowledge distillation. Given an input dataset for generating/training a text summarization model, neural architecture search is used to sample a search space to select a network architecture for the text summarization model. Knowledge distillation includes fine-tuning a language model for a given text summarization task using the input dataset, and using the fine-tuned language model as a teacher model to inform the selection of the network architecture and the training of the text summarization model. Once a text summarization model has been generated, the text summarization model can be used to generate summaries for given text.

Auto-creation of custom models for text summarization

Embodiments are disclosed for generating an intelligent change summary are described. In some embodiments, a method of generating an intelligent change summary includes obtaining a representation of a plurality of versions of a document, determining a distance score based on a comparison of a first of version of the document and a second version of the document, the distance score representing a magnitude of changes made from the first version of the document to the second version of the document, and generating a change summary of the document based on the distance score.

Intelligent change summarization for designers

Techniques for template generation from image content include extracting information associated with an input image. The information comprises: 1) layout information indicating positions of content corresponding to a content type of a plurality of content types within the input image; and 2) text attributes indicating at least a font of text included in the input image. A user-editable template having the characteristics of the input image is generated based on the layout information and the text attributes.

Semantically-guided template generation from image content

Certain embodiments involve using a gated convolutional encoder-decoder framework for applying affective characteristic labels to input text. For example, a method for identifying an affect label of text with a gated convolutional encoder-decoder model includes receiving, at a supervised classification engine, extracted linguistic features of an input text and a latent representation of an input text. The method also includes predicting, by the supervised classification engine, an affect characterization of the input text using the extracted linguistic features and the latent representation. Predicting the affect characterization includes normalizing and concatenating a linguistic feature representation generated from the extracted linguistic features with the latent representation to generate an appended latent representation. The method also includes identifying, by a gated convolutional encoder-decoder model, an affect label of the input text using the predicted affect characterization.

Detecting affective characteristics of text with gated convolutional encoder-decoder framework

Growing community of inventors

Hyderabad Telangana, India

Niyati Himanshu Chhaya