公开(公告)号：US20210192126A1

公开(公告)日：2021-06-24

申请号：US16721084

申请日：2019-12-19

Applicant: Adobe Inc.

Inventor： Sebastian Gehrmann ,  Franck Dernoncourt ,  Lidan Wang ,  Carl Dockhorn ,  Yu Gong

IPC: G06F40/169 ,  G06N20/00 ,  G06F40/117 ,  G06F3/0482 ,  G06F40/253 ,  G06F40/284

Abstract: The disclosure describes one or more embodiments of a structured text summary system that generates structured text summaries of digital documents based on an interactive graphical user interface. For example, the structured text summary system can collaborate with users to create structured text summaries of a digital document based on automatically generating document tags corresponding to the digital document, determining segments of the digital document that correspond to a selected document tag, and generating structured text summaries for those document segments.

公开(公告)号：US11709873B2

公开(公告)日：2023-07-25

申请号：US16741625

申请日：2020-01-13

Applicant: Adobe Inc.

Inventor： Jinfeng Xiao ,  Lidan Wang ,  Franck Dernoncourt ,  Trung Bui ,  Tong Sun

IPC: G06F16/33 ,  G06F16/953

CPC classification number: G06F16/3347 ,  G06F16/953

Abstract: Techniques and systems are provided for predicting answers in response to one or more input queries. For instance, text from a corpus of text can be processed by a reader to generate one or multiple question and answer spaces. A question and answer space can include answerable questions and the answers associated with the questions (referred to as “question and answer pairs”). A query defining a question can be received (e.g., from a user input device) and processed by a retriever portion of the system. The retriever portion of the system can retrieve an answer to the question from the one or more pre-constructed question and answer spaces, and/or can determine an answer by comparing one or more answers retrieved from the one or more pre-constructed question and answer spaces to an answer generated by a retriever-reader system.

公开(公告)号：US20210295191A1

公开(公告)日：2021-09-23

申请号：US16825531

申请日：2020-03-20

Applicant: Adobe Inc.

Inventor： Trung Bui ,  Lidan Wang ,  Franck Dernoncourt

IPC: G06N7/00 ,  G06N20/20 ,  G06N20/10 ,  G06N3/08 ,  G06K9/62

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for selecting hyper-parameter sets by utilizing a modified Bayesian optimization approach based on a combination of accuracy and training efficiency metrics of a machine learning model. For example, the disclosed systems can fit accuracy regression and efficiency regression models to observed metrics associated with hyper-parameter sets of a machine learning model. The disclosed systems can also implement a trade-off acquisition function that implements an accuracy-training efficiency balance metric to explore the hyper-parameter feature space and select hyper-parameters for training the machine learning model considering a balance between accuracy and training efficiency.

公开(公告)号：US20210216577A1

公开(公告)日：2021-07-15

申请号：US16741625

申请日：2020-01-13

Applicant: Adobe Inc.

Inventor： Jinfeng Xiao ,  Lidan Wang ,  Franck Dernoncourt ,  Trung Bui ,  Tong Sun

IPC: G06F16/33 ,  G06F16/953

Abstract: Techniques and systems are provided for predicting answers in response to one or more input queries. For instance, text from a corpus of text can be processed by a reader to generate one or multiple question and answer spaces. A question and answer space can include answerable questions and the answers associated with the questions (referred to as “question and answer pairs”). A query defining a question can be received (e.g., from a user input device) and processed by a retriever portion of the system. The retriever portion of the system can retrieve an answer to the question from the one or more pre-constructed question and answer spaces, and/or can determine an answer by comparing one or more answers retrieved from the one or more pre-constructed question and answer spaces to an answer generated by a retriever-reader system.

公开(公告)号：US11556826B2

公开(公告)日：2023-01-17

申请号：US16825531

申请日：2020-03-20

Applicant: Adobe Inc.

Inventor： Trung Bui ,  Lidan Wang ,  Franck Dernoncourt

IPC: G06N7/00 ,  G06N20/20 ,  G06N20/10 ,  G06K9/62 ,  G06N3/08 ,  G06V10/75

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for selecting hyper-parameter sets by utilizing a modified Bayesian optimization approach based on a combination of accuracy and training efficiency metrics of a machine learning model. For example, the disclosed systems can fit accuracy regression and efficiency regression models to observed metrics associated with hyper-parameter sets of a machine learning model. The disclosed systems can also implement a trade-off acquisition function that implements an accuracy-training efficiency balance metric to explore the hyper-parameter feature space and select hyper-parameters for training the machine learning model considering a balance between accuracy and training efficiency.

公开(公告)号：US20220138534A1

公开(公告)日：2022-05-05

申请号：US17087881

申请日：2020-11-03

Applicant: Adobe Inc.

Inventor： Amir Pouran Ben Veyseh ,  Franck Dernoncourt ,  Quan Tran ,  Lidan Wang

IPC: G06N3/04 ,  G06F40/30 ,  G06F40/295 ,  G06F17/16

Abstract: This disclosure describes methods, non-transitory computer readable storage media, and systems that utilize a plurality of neural networks to determine structural and semantic information via different views of a word sequence and then utilize this information to extract a relationship between word sequence entities. For example, the disclosed systems generate a plurality of sets of encoded word representation vectors utilizing the plurality of neural networks. The disclosed system then extracts the relationship from an overall word representation vector generated based on the sets of encoded word representation vectors. Furthermore, the disclosed system enforces structural and semantic consistency between views via a plurality of constrains involving a control mechanism for the semantic view and a plurality of losses.

公开(公告)号：US11222167B2

公开(公告)日：2022-01-11

申请号：US16721084

申请日：2019-12-19

Applicant: Adobe Inc.

Inventor： Sebastian Gehrmann ,  Franck Dernoncourt ,  Lidan Wang ,  Carl Dockhorn ,  Yu Gong

IPC: G06F17/00 ,  G06F40/169 ,  G06N20/00 ,  G06F40/284 ,  G06F3/0482 ,  G06F40/253 ,  G06F40/117

Abstract: The disclosure describes one or more embodiments of a structured text summary system that generates structured text summaries of digital documents based on an interactive graphical user interface. For example, the structured text summary system can collaborate with users to create structured text summaries of a digital document based on automatically generating document tags corresponding to the digital document, determining segments of the digital document that correspond to a selected document tag, and generating structured text summaries for those document segments.

公开(公告)号：US12061995B2

公开(公告)日：2024-08-13

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: G06N7/01 ,  G06F40/205 ,  G06F40/279 ,  G06F40/30 ,  G06N20/00

CPC classification number: G06N7/01 ,  G06F40/205 ,  G06F40/279 ,  G06F40/30 ,  G06N20/00

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：US11893345B2

公开(公告)日：2024-02-06

申请号：US17223166

申请日：2021-04-06

Applicant: ADOBE INC.

Inventor： Amir Pouran Ben Veyseh ,  Franck Dernoncourt ,  Quan Tran ,  Varun Manjunatha ,  Lidan Wang ,  Rajiv Jain ,  Doo Soon Kim ,  Walter Chang

IPC: G06F40/284 ,  G06F40/211 ,  G06F40/30 ,  G06N3/08 ,  G06F40/126 ,  G06N3/044 ,  G06N3/045

CPC classification number: G06F40/284 ,  G06F40/126 ,  G06F40/211 ,  G06F40/30 ,  G06N3/044 ,  G06N3/045 ,  G06N3/08

Abstract: Systems and methods for natural language processing are described. One or more embodiments of the present disclosure receive a document comprising a plurality of words organized into a plurality of sentences, the words comprising an event trigger word and an argument candidate word, generate word representation vectors for the words, generate a plurality of document structures including a semantic structure for the document based on the word representation vectors, a syntax structure representing dependency relationships between the words, and a discourse structure representing discourse information of the document based on the plurality of sentences, generate a relationship representation vector based on the document structures, and predict a relationship between the event trigger word and the argument candidate word based on the relationship representation vector.

公开(公告)号：US11620457B2

公开(公告)日：2023-04-04

申请号：US17177372

申请日：2021-02-17

Applicant: ADOBE INC.

Inventor： Logan Lebanoff ,  Franck Dernoncourt ,  Doo Soon Kim ,  Lidan Wang ,  Walter Chang

IPC: G06F40/40 ,  G06F40/284 ,  G06F40/166 ,  G06N3/04 ,  G06N3/08 ,  G06F40/30

Abstract: Systems and methods for sentence fusion are described. Embodiments receive coreference information for a first sentence and a second sentence, wherein the coreference information identifies entities associated with both a term of the first sentence and a term of the second sentence, apply an entity constraint to an attention head of a sentence fusion network, wherein the entity constraint limits attention weights of the attention head to terms that correspond to a same entity of the coreference information, and predict a fused sentence using the sentence fusion network based on the entity constraint, wherein the fused sentence combines information from the first sentence and the second sentence.