Adobe, Inc.

Pranav Ravindra Maneriker

Natwar Modani

Balaji Vasan Srinivasan

Atanu Ranjan Sinha

Anandhavelu Natarajan

Atanu R Sinha

Ritwik Sinha

Gaurush Hiranandani

Sopan Khosla

Dhruv Singal

Cedric Huesler

Kundan Krishna

Shivani Gupta

Reshmi Naduparambil Sasidharan

Vivek Gupta

Basava Raj K

Vaishnavi Subramanian

Utpal

Niyati Himanshu Chhaya

Vishwa Vinay

Shiv Kumar Saini

Tanya Goyal

Virgil-Artimon Palanciuc

Meghanath Macha Yadagiri

Anandha Velu Natarajan

Tharun Mohandoss

Navjot Singh

Manish Dash

Avani Samdariya

In some embodiments, an intervention evaluation system estimates counterfactual metric for a focal online platform based on an assessment model built using performance data of the focal online platform and control online platforms. The intervention evaluation system accesses performance data of the focal online platform that has been subject to a temporary intervention and performance data of control online platforms that are not subject to the temporary intervention. The intervention evaluation system determines estimation weights for these control online platforms based on the performance data in a pre-intervention period. Based on the estimation weights, the intervention evaluation system computes a counterfactual metric indicating the performance of the focal online platform in a post-intervention period in the absence of the temporary intervention. The counterfactual metric is transmitted to the focal online platform, where the counterfactual metric is usable for modifying an interactive computing environment provided by the focal online platform.

Facilitating changes to online computing environment by assessing impacts of temporary interventions

Embodiments of the present invention provide systems, methods, and computer storage media directed to facilitating predicting style breaches within content. In one embodiment, target content for which style breach prediction is desired is obtained. Style features associated with the target content are identified. Such style features and a style breach prediction model are used to predict a style breach within the target content, the style breach indicating a change of style used within the target content (e.g., a single document).

Predicting style breaches within textual content

Various embodiments describe user segmentation. In an example, potential rules are generated by applying a frequency-based analysis to user interaction data points. Each of the potential rules includes a set of attributes of the user interaction data points and indicates that these data points belong to a segment of interest. An objective function is used to select an optimal set of rules from the potential rules for the segment of interest. The potential rules are used as variable inputs to the objective function and this function is optimized based on interpretability and accuracy parameters. Each rule from the optimal set is associated with a group of the segment of interest. The user interaction data points are segments into the groups by matching attributes of these data points with the rules.

Accurate and interpretable rules for user segmentation

A fact replacement and style consistency tool is described. Rather than rely heavily on human involvement to replace facts and maintain consistent styles across multiple digital documents, the described change management system identifies factual and stylistic inconsistencies between these documents, in part, using natural language processing techniques. Once these inconsistencies are identified, the change management system generates a user interface that includes indications of the inconsistencies and information describing them, e.g., an indication noting not only a type of inconsistency but also presenting a first portion and at least a second portion of the multiple documents that are factually inconsistent. By automatically identifying these factual and stylistic inconsistencies across multiple documents and presenting indications of such cross-document inconsistencies, the described change management system eliminates human errors in connection with maintaining factual and stylistic consistency over a body of documents.

Fact replacement and style consistency tool

Modifications to the DiD technique are disclosed which provide an estimate of the effectiveness of a site-wide action where no control group exists within the data subsequent to implementation of the site-wide action. In some examples, a method may include identifying a treatment group based on a modified treatment period, selecting a control group from a control period prior to the modified treatment period, and performing a modified difference-in-differences (DiD) estimation for a metric based on the modified treatment period, the treatment group, the control period, and the control group. The modified treatment period may encompass an intervention of a site-wide action, and include a pre-intervention time period and a post-intervention time period.

Techniques to quantify effectiveness of site-wide actions

Embodiments of the present invention provide systems, methods, and computer storage media directed to facilitating corpus-based content generation, in particular, using graph-based multi-sentence compression to generate a final content output. In one embodiment, pre-existing source content is identified and retrieved from a corpus. The source content is then parsed into sentence tokens, mapped and weighted. The sentence tokens are further parsed into word tokens and weighted. The mapped word tokens are then compressed into candidate sentences to be used in a final content. The final content is assembled using ranked candidate sentences, such that the final content is organized to reduce information redundancy and optimize content cohesion.

Constructing content based on multi-sentence compression of source content

Systems and techniques for identifying segments in categorical data include receiving multiple transaction ID (TID) lists with univariate values that satisfy a thresholding metric with each TID list representing an occurrence of a single attribute in a set of transactions. The TID lists are stored with the univariate values that satisfy the thresholding metric in a data structure. In a loop, candidate itemsets to form from combinations of TID lists are determined using only the combinations of TID lists that satisfy categorical constraints. In the loop, for the candidate itemsets that satisfy categorical constraints, both the thresholding metric and a similarity metric are applied to the candidate itemsets. Final itemsets are formed from only the candidate itemsets that satisfy both the thresholding metric and the similarity metric.

Identifying high value segments in categorical data

Embodiments are disclosed for bundling and arranging online content fragments for presentation based on content-specific metrics and inter-content constraints. For example, a content management application accesses candidate content fragments, a content-specific metric, and an inter-content constraint. The content management application computes minimum and maximum contribution values for the candidate content fragments. The content management application selects, based on the computed minimum and maximum contribution values, a subset of the candidate content fragments. The content management application applies, subject to the inter-content constraint, a bundle-selection function to the selected candidate content fragments and thereby identifies a bundle of online content fragments. The content management application outputs the identified bundle of online content fragments for presentation via an online service.

Bundling online content fragments for presentation based on content-specific metrics and inter-content constraints

Multimedia document summarization techniques are described. That is, given a document that includes text and a set of images, various implementations generate a summary by extracting relevant text segments in the document and relevant segments of images with constraints on the amount of text and number/size of images in the summary.

Multimedia document summarization

A quality metric of a multimedia summary of a multimedia content item is determined based, in part, on semantic similarities of the summary and content item, rather than just on word frequencies. This is accomplished in some embodiments by identifying a semantic meaning of the summary and multimedia content item using vector analysis. The vectors of the summary and the vectors of the multimedia content item are compared to determine semantic similarity. In other examples, the quality metric of the multimedia summary is determined based on, in part, a coherence between an image portion of a summary and a text portion of the summary for determining a quality metric of a multimedia summary.

Determining quality of a summary of multimedia content

Growing community of inventors

Bengaluru, India

Pranav Ravindra Maneriker