公开(公告)号：US20250103822A1

公开(公告)日：2025-03-27

申请号：US18372462

申请日：2023-09-25

Applicant: Adobe Inc.

Inventor： Niranjan Kumbi ,  Sreekanth Reddy ,  Sumit Bhatia ,  Milan Aggarwal ,  Simra Shahid ,  Nikitha Srikanth ,  Camille Girabawe ,  Narayanan Seshadri

IPC: G06F40/35

Abstract: System and methods for generating, validating, and augmenting question-answer pairs using generative AI are provided. An online interaction server accesses a set of digital content available at a set of designated network locations. The online interaction server further trains a pre-trained large language model (LLM) using the set of digital content to obtain a customized LLM. The online interaction server generates a set of question-answer pairs based on the set of digital content using the customized LLM and validates the set of question-answer pairs by determining if an answer in a question-answer pair is derived from the set of digital content. The online interaction server also selects a digital asset to augment an answer in a validated question-answer pair based on a semantic similarity between the validated question-answer pair and the digital asset.

公开(公告)号：US11960520B2

公开(公告)日：2024-04-16

申请号：US17853141

申请日：2022-06-29

Applicant: Adobe Inc.

Inventor： Tanay Anand ,  Sumit Bhatia ,  Simra Shahid ,  Nikitha Srikanth ,  Nikaash Puri

IPC: G06F16/30 ,  G06F16/33 ,  G06F16/35 ,  G06F16/93 ,  G06F18/2133 ,  G06F18/2413 ,  G06F40/30

CPC classification number: G06F16/35 ,  G06F16/3347 ,  G06F16/93 ,  G06F18/2133 ,  G06F18/24147 ,  G06F40/30

Abstract: Some techniques described herein relate to generating a hierarchical topic model (HTM), which can be used to generate custom content. In one example, a method includes determining first-level topics in a topic hierarchy related to a corpus of documents. A first-level topic of the first-level topics includes multiple words. The multiple words are grouped into clusters based on word embeddings of the multiple words. The multiple words are then subdivided into second-level topics as subtopics of the first-level topic, such that the number of second-level topics equals the number of clusters. A document of the corpus of documents is assigned to the first-level topic and to a second-level topic of the second-level topics, and an indication is received of access by a user to the document. Custom content is generated for the user based on one or more other documents assigned to the first-level topic and the second-level topic.

公开(公告)号：US11997056B2

公开(公告)日：2024-05-28

申请号：US17897419

申请日：2022-08-29

Applicant: ADOBE INC.

Inventor： Sumit Bhatia ,  Jivat Neet Kaur ,  Rachit Bansal ,  Milan Aggarwal ,  Balaji Krishnamurthy

IPC: H04L51/02 ,  G06F40/295 ,  G06N5/022

CPC classification number: H04L51/02 ,  G06F40/295 ,  G06N5/022

Abstract: The technology described herein receives a natural-language sequence of words comprising multiple entities. The technology then identifies a plurality of entities in the natural-language sequence. The technology generates a masked natural-language sequence by masking a first entity in the natural-language sequence. The technology retrieves, from a knowledge base, information related to a second entity in the plurality of entities. The technology then trains a natural-language model to respond to a query. The training uses a first representation of the masked natural-language sequence, a second representation of the information, and the first entity.

公开(公告)号：US20240004912A1

公开(公告)日：2024-01-04

申请号：US17853141

申请日：2022-06-29

Applicant: Adobe Inc.

Inventor： Tanay Anand ,  Sumit Bhatia ,  Simra Shahid ,  Nikitha Srikanth ,  Nikaash Puri

IPC: G06F16/35 ,  G06K9/62 ,  G06F16/93 ,  G06F40/30 ,  G06F16/33

CPC classification number: G06F16/35 ,  G06K9/6239 ,  G06K9/6276 ,  G06F16/93 ,  G06F40/30 ,  G06F16/3347

Abstract: Some techniques described herein relate to generating a hierarchical topic model (HTM), which can be used to generate custom content. In one example, a method includes determining first-level topics in a topic hierarchy related to a corpus of documents. A first-level topic of the first-level topics includes multiple words. The multiple words are grouped into clusters based on word embeddings of the multiple words. The multiple words are then subdivided into second-level topics as subtopics of the first-level topic, such that the number of second-level topics equals the number of clusters. A document of the corpus of documents is assigned to the first-level topic and to a second-level topic of the second-level topics, and an indication is received of access by a user to the document. Custom content is generated for the user based on one or more other documents assigned to the first-level topic and the second-level topic.

公开(公告)号：US20230153534A1

公开(公告)日：2023-05-18

申请号：US17526824

申请日：2021-11-15

Applicant: ADOBE INC.

Inventor： Rachit Bansal ,  Milan Aggarwal ,  Sumit Bhatia ,  Jivat Neet Kaur ,  Balaji Krishnamurthy

IPC: G06F40/295 ,  G06F16/332 ,  G06N20/00

CPC classification number: G06F40/295 ,  G06F16/3329 ,  G06N20/00

Abstract: Methods and systems are provided for facilitating generation and utilization of a commonsense contextualizing machine learning (ML) model, in accordance with embodiments described herein. In embodiments, a commonsense contextual ML model is trained by fine-tuning a pre-trained language model using a set of training path-sentence pairs. Each training path-sentence pair includes a commonsense path, identified via a commonsense knowledge graph, and a natural language sentence identified as contextually related to the commonsense path. The trained commonsense contextualizing ML model can then be used to generate a commonsense inference path for a text input. Such a commonsense inference path can include a sequence of entities and relations that provide commonsense context to the text input. Thereafter, the commonsense inference path can be provided to a natural language processing system for use in performing a natural language processing task.