Adobe, Inc.

Natwar Modani

Balaji Vasan Srinivasan

Gaurush Hiranandani

Pranav Ravindra Maneriker

Niyati Himanshu Chhaya

Harsh Jhamtani

Shiv Kumar Saini

Paridhi Maheshwari

Cedric Huesler

Aparna Garimella

Atanu R Sinha

Shivani Gupta

Inderjeet Jayakumar Nair

Harsh Deshpande

Diviya Singh

Vaishnavi Subramanian

Utpal

Srinivas Saurab Sirpurkar

Franck Dernoncourt

Trung Huu Bui

Vishwa Vinay

Sumit Shekhar

Iftikhar Ahamath Burhanuddin

Tong Sun

Tanya Goyal

Sopan Khosla

Sanket Vaibhav Mehta

Srikrishna Karanam

Jonas Dahl

Lidan Wang

Kundan Krishna

Ani Nenkova

Anandha Velu Natarajan

Manoj Kilaru

Navita Goyal

Rishiraj Saha Roy

Manas Agarwal

Garvit Bhardwaj

Akhash N A

Vishesh Kaushik

Muskan Agarwal

Priyanshu Agarwal

Ayush Maheshwari

Vaidehi Ramesh Patil

Gaurav Verma

Anurag Maurya

Anirudh Kanfade

Inderjeet Nair

Sachin Kelkar

Jeenu Grover

Techniques described herein are directed to assisting review of documents. In one embodiment, one or more text segments and one or more subjects in a document are identified. A text segment in the document is associated with a corresponding subject identified in the document. The text segment is classified with a content type value corresponding to a relation of the text segment to the corresponding subject. Thereafter, information is provided for the text segment associated with the corresponding subject for display on a user interface. Such information can include a representation of the content type value for the text segment.

Assisted review of text content using a machine learning model

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

In implementations of systems for generating indications of relationships between electronic documents, a processing device implements a relationship system to segment text of electronic documents included in a document corpus into segments. The relationship system determines a subset of the electronic documents that includes electronic document pairs having a number of similar segments that is greater than a threshold number. The similar segments are identified using locality sensitive hashing. The electronic document pairs are classified as related documents or unrelated documents using a machine learning model that receives a pair of electronic documents as an input and generates an indication of a classification for the pair of electronic documents as an output. Indications of relationships between particular electronic documents included in the subset are generated based at least partially on the electronic document pairs that are classified as related documents.

Systems for generating indications of relationships between electronic documents

Methods and systems are provided herein for summarizing a set of anomalies corresponding to a group of metrics of interest to a monitoring system user. Initially, a set of anomalies corresponding to a group of metrics is identified as having values that are outside of a predetermined range. A correlation value is determined for at least a portion of pairs of anomalies in the set of anomalies. For each anomaly in the set of anomalies, an informativeness value is computed that indicates how informative each anomaly in the set of anomalies is to the monitoring system user. The correlation values and the informativeness values are then used to identify at least one key anomaly and a plurality of non-key anomalies from the set of anomalies. A summary is generated of the identified at least one key anomaly to provide information to the monitoring system user about the set of anomalies for a particular time period.

Providing personalized alerts and anomaly summarization

Methods for natural language semantic matching performed by training and using a Markov Network model are provided. The trained Markov Network model can be used to identify answers to questions. Training may be performed using question-answer pairs that include labels indicating a correct or incorrect answer to a question. The trained Markov Network model can be used to identify answers to questions from sources stored on a database. The Markov Network model provides superior performance over other semantic matching models, in particular, where the training data set includes a different information domain type relative to the input question or the output answer of the trained Markov Network model.

Learning with limited supervision for question-answering with light-weight Markov models

Methods and systems are provided for facilitating generation of fillable document templates. In embodiments, a document having a plurality of tokens is obtained. Using a machine learned model, a token state is identified for each token of the plurality of tokens. Each token state indicates whether a corresponding token is a static token that is to be included in a fillable document template or a dynamic token that is to be excluded in the fillable document template. Thereafter, a fillable document template corresponding with the document is generated, wherein for each dynamic token of the document, the fillable document template includes a fillable field corresponding to the respective dynamic token.

Facilitating generation of fillable document templates

Techniques are described for intelligently identifying concept labels for a set of multiple documents where the identified concept labels are representative of and semantically relevant to the information contained by the set of documents. The technique includes extracting semantic units (e.g., paragraphs) from the set of documents and determining concept labels applicable to the semantic units based on relevance scores computed for the concept labels. The technique includes determining an initial set of concept labels for the set of documents based on the applicable concept labels. The technique further includes obtaining a reference hierarchy associated with the reference set of concept labels and determining a final set of concept labels for the set of documents using a reference hierarchy, the initial set of concept labels, and the relevance scores. The technique includes outputting information identifying the final set of concept labels for the set of documents.

Automated identification of concept labels for a set of documents

A technique for intelligently identifying concept labels for a text fragment where the identified concept labels are representative of and semantically relevant to the information contained by the text fragment is provided. The technique includes determining, using a knowledge base storing information for a reference set of concept labels, a first subset of concept labels that are relevant to the information contained by the text fragment. The technique includes ordering the first subset of concept labels according to their relevance scores and performing dependency analysis on the ordered list of concept labels. Based on the dependency analysis, the technique includes identifying concept labels for a text fragment that are more independent (e.g., more distinct and non-overlapping) of each other, representative of and semantically relevant to the information represented by the text fragment.

Automated identification of concept labels for a text fragment

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

In various implementations, a method includes receiving a set of time series data that corresponds to a metric. A seasonal pattern is extracted from the set of time series data and the extracted seasonal pattern is filtered from the set of time series data. A predictive model is generated from the filtered set of data. The extracted seasonal pattern is filtered from another set of time series data where the second set of time series data corresponds to the metric. The filtered second set of time series data is compared to the predictive model. An alert is generated to a user for a value within the filtered second set of time series data which falls outside of the predictive model.

Anomaly detection for time series data having arbitrary seasonality

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

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

Systems and methods provide for expanding user-provided content. User-provided input content is received via a user interface. Content that is relevant to the user-provided input content is identified from a repository of previously-generated content. The identified relevant content is divided into content sub-segments. From the content sub-segments, one or more pieces of candidate content are identified based on each content sub-segment's relevance to the received input content. At least one piece of identified candidate content is provided for display. A selection of one or more pieces of identified candidate content is received, such that the selected piece(s) of identified candidate content is appended to the received input content, thereby expanding the user-provided content.

Expanding input content utilizing previously-generated content

This disclosure generally covers systems and methods that identify and differentiate types of changes made from one version of a document to another version of the document. In particular, the disclosed systems and methods identify changes between different document versions as factual changes or paraphrasing changes or (in some embodiments) as changes of a more specific revision category. Moreover, in some embodiments, the disclosed systems and methods also generate a comparison of the first and second versions that identifies changes as factual changes or paraphrasing changes or (in some embodiments) as changes of a more specific revision category. The disclosed systems and methods, in some embodiments, further rank sentences that include changes made between different document versions or group similar (or the same) type of changes within a comparison of document versions.

Classifying and ranking changes between document versions

A method for generating summaries includes selecting a first subset of text units of a text composition to incorporate into a first summary of the text composition using a weighting of the text units that indicates for each text unit a relative importance of including the text unit in summaries of the text composition. The weighting of the text units is modified to reduce the relative importance of each text unit in the first subset based on the text unit having been selected for the first subset. A second subset of the text units is selected to incorporate into a second summary of the text composition using the modified weighting of the text units. At least one of the first summary and the second summary are provided to a user device.

Probabalistic generation of diverse summaries

Growing community of inventors

Bengaluru, India

Natwar Modani