公开(公告)号：US20250022252A1

公开(公告)日：2025-01-16

申请号：US18899571

申请日：2024-09-27

Applicant: Adobe Inc.

Inventor： Khoi Pham ,  Kushal Kafle ,  Zhe Lin ,  Zhihong Ding ,  Scott Cohen ,  Quan Tran

IPC: G06V10/75 ,  G06F18/214 ,  G06F18/25 ,  G06N3/08

Abstract: This disclosure describes one or more implementations of systems, non-transitory computer-readable media, and methods that extract multiple attributes from an object portrayed in a digital image utilizing a multi-attribute contrastive classification neural network. For example, the disclosed systems utilize a multi-attribute contrastive classification neural network that includes an embedding neural network, a localizer neural network, a multi-attention neural network, and a classifier neural network. In some cases, the disclosed systems train the multi-attribute contrastive classification neural network utilizing a multi-attribute, supervised-contrastive loss. In some embodiments, the disclosed systems generate negative attribute training labels for labeled digital images utilizing positive attribute labels that correspond to the labeled digital images.

公开(公告)号：US11544456B2

公开(公告)日：2023-01-03

申请号：US16810345

申请日：2020-03-05

Applicant: ADOBE INC.

Inventor： Khalil Mrini ,  Walter Chang ,  Trung Bui ,  Quan Tran ,  Franck Dernoncourt

IPC: G06F40/211 ,  G06N3/04 ,  G06N3/08

Abstract: Systems and methods for parsing natural language sentences using an artificial neural network (ANN) are described. Embodiments of the described systems and methods may generate a plurality of word representation matrices for an input sentence, wherein each of the word representation matrices is based on an input matrix of word vectors, a query vector, a matrix of key vectors, and a matrix of value vectors, and wherein a number of the word representation matrices is based on a number of syntactic categories, compress each of the plurality of word representation matrices to produce a plurality of compressed word representation matrices, concatenate the plurality of compressed word representation matrices to produce an output matrix of word vectors, and identify at least one word from the input sentence corresponding to a syntactic category based on the output matrix of word vectors.

公开(公告)号：US11120801B2

公开(公告)日：2021-09-14

申请号：US17086805

申请日：2020-11-02

Applicant: Adobe Inc.

Inventor： Quan Tran ,  Trung Bui ,  Hung Bui

IPC: G10L15/22 ,  G10L15/16 ,  G06N3/10 ,  G06N3/04 ,  G10L15/30

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating dialogue responses based on received utterances utilizing an independent gate context-dependent additive recurrent neural network. For example, the disclosed systems can utilize a neural network model to generate a dialogue history vector based on received utterances and can use the dialogue history vector to generate a dialogue response. The independent gate context-dependent additive recurrent neural network can remove local context to reduce computation complexity and allow for gates at all time steps to be computed in parallel. The independent gate context-dependent additive recurrent neural network maintains the sequential nature of a recurrent neural network using the hidden vector output.

公开(公告)号：US20250022459A1

公开(公告)日：2025-01-16

申请号：US18220910

申请日：2023-07-12

Applicant: Adobe Inc.

Inventor： Viet Dac Lai ,  Trung Bui ,  Seunghyun Yoon ,  Quan Tran ,  Hao Tan ,  Hanieh Deilamsalehy ,  Abel Salinas ,  Franck Dernoncourt

IPC: G10L15/183 ,  G10L15/065

Abstract: The disclosed method generates helpful training data for a language model, for example, a model implementing a punctuation restoration task, for real-world ASR texts. The method uses a reinforcement learning method using a generative AI model to generate additional data to train the language model. The method allows the generative AI model to learn from real-world ASR text to generate more effective training examples based on gradient feedback from the language 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：US11113479B2

公开(公告)日：2021-09-07

申请号：US16569513

申请日：2019-09-12

Applicant: Adobe Inc.

Inventor： Quan Tran ,  Tuan Manh Lai ,  Trung Bui

IPC: G06F40/00 ,  G06F40/44 ,  G06N5/04 ,  G06K9/62 ,  G06F17/16 ,  G06F16/9032

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that can determine an answer to a query based on matching probabilities for combinations of respective candidate answers. For example, the disclosed systems can utilize a gated-self attention mechanism (GSAM) to interpret inputs that include contextual information, a query, and candidate answers. The disclosed systems can also utilize a memory network in tandem with the GSAM to form a gated self-attention memory network (GSAMN) to refine outputs or predictions over multiple reasoning hops. Further, the disclosed systems can utilize transfer learning of the GSAM/GSAMN from an initial training dataset to a target training dataset.

公开(公告)号：US20210081503A1

公开(公告)日：2021-03-18

申请号：US16569513

申请日：2019-09-12

Applicant: Adobe Inc.

Inventor： Quan Tran ,  Tuan Manh Lai ,  Trung Bui

IPC: G06F17/28 ,  G06N5/04 ,  G06F16/9032 ,  G06F17/16 ,  G06K9/62

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that can determine an answer to a query based on matching probabilities for combinations of respective candidate answers. For example, the disclosed systems can utilize a gated-self attention mechanism (GSAM) to interpret inputs that include contextual information, a query, and candidate answers. The disclosed systems can also utilize a memory network in tandem with the GSAM to form a gated self-attention memory network (GSAMN) to refine outputs or predictions over multiple reasoning hops. Further, the disclosed systems can utilize transfer learning of the GSAM/GSAMN from an initial training dataset to a target training dataset.

公开(公告)号：US20230197081A1

公开(公告)日：2023-06-22

申请号：US18107620

申请日：2023-02-09

Applicant: Adobe Inc.

Inventor： Tuan Manh Lai ,  Trung Bui ,  Quan Tran

IPC: G10L15/22 ,  G10L15/02

CPC classification number: G10L15/22 ,  G10L15/02 ,  G10L15/183

Abstract: A computer-implemented method is disclosed for determining one or more characteristics of a dialog between a computer system and user. The method may comprise receiving a system utterance comprising one or more tokens defining one or more words generated by the computer system; receiving a user utterance comprising one or more tokens defining one or more words uttered by a user in response to the system utterance, the system utterance and the user utterance forming a dialog context; receiving one or more utterance candidates comprising one or more tokens; for each utterance candidate, generating an input sequence combining the one or more tokens of each of the system utterance, the user utterance, and the utterance candidate; and for each utterance candidate, evaluating the generated input sequence with a model to determine a probability that the utterance candidate is relevant to the dialog context.

公开(公告)号：US20220383037A1

公开(公告)日：2022-12-01

申请号：US17332734

申请日：2021-05-27

Applicant: Adobe Inc.

Inventor： Khoi Pham ,  Kushal Kafle ,  Zhe Lin ,  Zhihong Ding ,  Scott Cohen ,  Quan Tran

IPC: G06K9/62 ,  G06N3/08

Abstract: This disclosure describes one or more implementations of systems, non-transitory computer-readable media, and methods that extract multiple attributes from an object portrayed in a digital image utilizing a multi-attribute contrastive classification neural network. For example, the disclosed systems utilize a multi-attribute contrastive classification neural network that includes an embedding neural network, a localizer neural network, a multi-attention neural network, and a classifier neural network. In some cases, the disclosed systems train the multi-attribute contrastive classification neural network utilizing a multi-attribute, supervised-contrastive loss. In some embodiments, the disclosed systems generate negative attribute training labels for labeled digital images utilizing positive attribute labels that correspond to the labeled digital images.

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.