公开(公告)号：US11354513B2

公开(公告)日：2022-06-07

申请号：US16784000

申请日：2020-02-06

Applicant: Adobe Inc.

Inventor： Natwar Modani ,  Srinivas Saurab Sirpurkar ,  Paridhi Maheshwari ,  Harsh Deshpande ,  Diviya Singh

IPC: G06F40/279 ,  G06F40/131 ,  G06F40/30 ,  G06F9/30 ,  G06F40/216 ,  G06V30/416

Abstract: 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.

公开(公告)号：US20210279622A1

公开(公告)日：2021-09-09

申请号：US16813098

申请日：2020-03-09

Applicant: ADOBE INC.

Inventor： Trung Huu Bui ,  Tong Sun ,  Natwar Modani ,  Lidan Wang ,  Franck Dernoncourt

IPC: G06N7/00 ,  G06N20/00 ,  G06F40/205 ,  G06F40/279 ,  G06F40/30

Abstract: 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.

公开(公告)号：US20210248323A1

公开(公告)日：2021-08-12

申请号：US16784145

申请日：2020-02-06

Applicant: Adobe Inc.

Inventor： Paridhi Maheshwari ,  Harsh Deshpande ,  Diviya Singh ,  Natwar Modani ,  Srinivas Saurab Sirpurkar

IPC: G06F40/30 ,  G06K9/00 ,  G06F40/216

Abstract: 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.

公开(公告)号：US20190197184A1

公开(公告)日：2019-06-27

申请号：US15854320

申请日：2017-12-26

Applicant: ADOBE INC.

Inventor： Balaji Vasan Srinivasan ,  Pranav Ravindra Maneriker ,  Natwar Modani ,  Kundan Krishna

IPC: G06F17/30 ,  G06F17/27

CPC classification number: G06F16/334 ,  G06F16/338 ,  G06F17/2705 ,  G06F17/277

Abstract: 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.

公开(公告)号：US20230162518A1

公开(公告)日：2023-05-25

申请号：US17534744

申请日：2021-11-24

Applicant: Adobe Inc.

Inventor： Natwar Modani ,  Vaidehi Ramesh Patil ,  Inderjeet Jayakumar Nair ,  Gaurav Verma ,  Anurag Maurya ,  Anirudh Kanfade

IPC: G06V30/413 ,  G06V30/262 ,  G06V30/414 ,  G06V30/418

CPC classification number: G06V30/413 ,  G06V30/274 ,  G06V30/414 ,  G06V30/418

Abstract: 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.

公开(公告)号：US11416684B2

公开(公告)日：2022-08-16

申请号：US16784145

申请日：2020-02-06

Applicant: Adobe Inc.

Inventor： Paridhi Maheshwari ,  Harsh Deshpande ,  Diviya Singh ,  Natwar Modani ,  Srinivas Saurab Sirpurkar

IPC: G06F40/137 ,  G06F40/237 ,  G06F40/279 ,  G06F40/30 ,  G06F40/216 ,  G06V30/416

Abstract: 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.

公开(公告)号：US10713432B2

公开(公告)日：2020-07-14

申请号：US15476640

申请日：2017-03-31

Applicant: Adobe Inc.

Inventor： Tanya Goyal ,  Sachin Kelkar ,  Natwar Modani ,  Manas Agarwal ,  Jeenu Grover

IPC: G06F17/00 ,  G06F40/194 ,  G06F40/117 ,  G06F40/166 ,  G06F40/197

Abstract: 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.

公开(公告)号：US20240303496A1

公开(公告)日：2024-09-12

申请号：US18181044

申请日：2023-03-09

Applicant: ADOBE INC.

Inventor： Inderjeet Jayakumar Nair ,  Natwar Modani

IPC: G06N3/0895 ,  G06F40/279

CPC classification number: G06N3/0895 ,  G06F40/279

Abstract: A method, apparatus, non-transitory computer readable medium, and system of training a domain-specific language model are described. One or more aspects of the method, apparatus, non-transitory computer readable medium, and system include obtaining domain-specific training data including a plurality of domain-specific documents having a document structure corresponding to a domain, and obtaining domain-agnostic training data including a plurality of documents outside of the domain. The domain-specific training data and the domain-agnostic training data are used to train a language model to perform a domain-specific task based on the domain-specific training data and to perform a domain agnostic task based on the domain-agnostic training data.

公开(公告)号：US20210248322A1

公开(公告)日：2021-08-12

申请号：US16784000

申请日：2020-02-06

Applicant: Adobe Inc.

Inventor： Natwar Modani ,  Srinivas Saurab Sirpurkar ,  Paridhi Maheshwari ,  Harsh Deshpande ,  Diviya Singh

IPC: G06F40/30 ,  G06F40/216 ,  G06K9/00 ,  G06F9/30

Abstract: 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.

公开(公告)号：US11023577B2

公开(公告)日：2021-06-01

申请号：US15228570

申请日：2016-08-04

Applicant: ADOBE INC.

Inventor： Shiv Kumar Saini ,  Natwar Modani ,  Balaji Vasan Srinivasan

IPC: G06N20/00 ,  G06F21/55 ,  G06F11/34

Abstract: 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.