公开(公告)号：US11941508B2

公开(公告)日：2024-03-26

申请号：US17186566

申请日：2021-02-26

申请人： ADOBE INC.

发明人： Quan Tran ,  Franck Dernoncourt ,  Walter Chang

IPC分类号： G06F16/00 ,  G06F16/242 ,  G06N3/042 ,  G06N3/044 ,  G06N3/045 ,  G06N3/08

CPC分类号： G06N3/042 ,  G06F16/243 ,  G06N3/044 ,  G06N3/045 ,  G06N3/08

摘要： The present disclosure describes systems and methods for dialog processing and information retrieval. Embodiments of the present disclosure provide a dialog system (e.g., a task-oriented dialog system) with adaptive recurrent hopping and dual context encoding to receive and understand a natural language query from a user, manage dialog based on natural language conversation, and generate natural language responses. For example, a memory network can employ a memory recurrent neural net layer and a decision meta network (e.g., a subnet) to determine an adaptive number of memory hops for obtaining readouts from a knowledge base. Further, in some embodiments, a memory network uses a dual context encoder to encode information from original context and canonical context using parallel encoding layers.

公开(公告)号：US11630952B2

公开(公告)日：2023-04-18

申请号：US16518894

申请日：2019-07-22

申请人： Adobe Inc.

发明人： Sean MacAvaney ,  Franck Dernoncourt ,  Walter Chang ,  Seokhwan Kim ,  Doo Soon Kim ,  Chen Fang

IPC分类号： G06F17/15 ,  G06F17/16 ,  G06N3/045 ,  G06V10/80 ,  G06V10/82 ,  G06F40/279 ,  G06F18/2431 ,  G06V10/764 ,  G06V10/70

摘要： This disclosure relates to methods, non-transitory computer readable media, and systems that can classify term sequences within a source text based on textual features analyzed by both an implicit-class-recognition model and an explicit-class-recognition model. For example, by applying machine-learning models for both implicit and explicit class recognition, the disclosed systems can determine a class corresponding to a particular term sequence within a source text and identify the particular term sequence reflecting the class. The dual-model architecture can equip the disclosed systems to apply (i) the implicit-class-recognition model to recognize implicit references to a class in source texts and (ii) the explicit-class-recognition model to recognize explicit references to the same class in source texts.

公开(公告)号：US20210118430A1

公开(公告)日：2021-04-22

申请号：US17135629

申请日：2020-12-28

申请人： Adobe Inc.

发明人： Seokhwan Kim ,  Walter Chang

IPC分类号： G10L15/16 ,  G06F16/9032 ,  G10L15/22 ,  H04L12/58

摘要： The present disclosure relates to generating digital responses based on digital dialog states generated by a neural network having a dynamic memory network architecture. For example, in one or more embodiments, the disclosed system provides a digital dialog having one or more segments to a dialog state tracking neural network having a dynamic memory network architecture that includes a set of multiple memory slots. In some embodiments, the dialog state tracking neural network further includes update gates and reset gates used in modifying the values stored in the memory slots. For instance, the disclosed system can utilize cross-slot interaction update/reset gates to accurately generate a digital dialog state for each of the segments of digital dialog. Subsequently, the system generates a digital response for each segment of digital dialog based on the digital dialog state.

公开(公告)号：US20210004576A1

公开(公告)日：2021-01-07

申请号：US17025477

申请日：2020-09-18

申请人： Adobe Inc.

发明人： Trung Bui ,  Zhe Lin ,  Walter Chang ,  Nham Le ,  Franck Dernoncourt

IPC分类号： G06K9/00 ,  G06N3/04 ,  G10L15/26 ,  G10L15/25

摘要： The present disclosure relates to systems, methods, and non-transitory computer readable media for generating modified digital images based on verbal and/or gesture input by utilizing a natural language processing neural network and one or more computer vision neural networks. The disclosed systems can receive verbal input together with gesture input. The disclosed systems can further utilize a natural language processing neural network to generate a verbal command based on verbal input. The disclosed systems can select a particular computer vision neural network based on the verbal input and/or the gesture input. The disclosed systems can apply the selected computer vision neural network to identify pixels within a digital image that correspond to an object indicated by the verbal input and/or gesture input. Utilizing the identified pixels, the disclosed systems can generate a modified digital image by performing one or more editing actions indicated by the verbal input and/or gesture input.

公开(公告)号：US20200160042A1

公开(公告)日：2020-05-21

申请号：US16192573

申请日：2018-11-15

申请人： Adobe Inc.

发明人： Trung Bui ,  Zhe Lin ,  Walter Chang ,  Nham Le ,  Franck Dernoncourt

IPC分类号： G06K9/00 ,  G10L15/25 ,  G10L15/26 ,  G06N3/04

摘要： The present disclosure relates to systems, methods, and non-transitory computer readable media for generating modified digital images based on verbal and/or gesture input by utilizing a natural language processing neural network and one or more computer vision neural networks. The disclosed systems can receive verbal input together with gesture input. The disclosed systems can further utilize a natural language processing neural network to generate a verbal command based on verbal input. The disclosed systems can select a particular computer vision neural network based on the verbal input and/or the gesture input. The disclosed systems can apply the selected computer vision neural network to identify pixels within a digital image that correspond to an object indicated by the verbal input and/or gesture input. Utilizing the identified pixels, the disclosed systems can generate a modified digital image by performing one or more editing actions indicated by the verbal input and/or gesture input.

公开(公告)号：US20190392066A1

公开(公告)日：2019-12-26

申请号：US16019152

申请日：2018-06-26

申请人： Adobe Inc.

发明人： Doo Soon Kim ,  Walter Chang

IPC分类号： G06F17/30 ,  G06F17/27

摘要： Various embodiments describe techniques for retrieving query results for natural language procedural queries. A query answering (QA) system generates a structured semantic representation of a natural language query. The structured semantic representation includes terms in the natural language query and the relationship between the terms. The QA system retrieves a set of candidate query results for the natural language query from a repository, generates a structured semantic representation for each candidate query result, and determines a match score between the natural language query and each respective candidate query result based on the similarity between the structured semantic representations for the natural language query and each respective candidate query result. A candidate query result having the highest match score is selected as the query result for the natural language query. In some embodiments, paraphrasing rules are generated from user interaction data and are used to determine the match score.

公开(公告)号：US20190384807A1

公开(公告)日：2019-12-19

申请号：US16007632

申请日：2018-06-13

申请人： Adobe Inc.

发明人： Franck Dernoncourt ,  Walter Chang ,  Trung Bui ,  Sean Fitzgerald ,  Sasha Spala ,  Kishore Aradhya ,  Carl Dockhorn

IPC分类号： G06F17/24 ,  G06F17/30 ,  G06N3/08 ,  G06N3/04

摘要： Systems, methods, and non-transitory computer-readable media are disclosed that collect and analyze annotation performance data to generate digital annotations for evaluating and training automatic electronic document annotation models. In particular, in one or more embodiments, the disclosed systems provide electronic documents to annotators based on annotator topic preferences. The disclosed systems then identify digital annotations and annotation performance data such as a time period spent by an annotator in generating digital annotations and annotator responses to digital annotation questions. Furthermore, in one or more embodiments, the disclosed systems utilize the identified digital annotations and the annotation performance data to generate a final set of reliable digital annotations. Additionally, in one or more embodiments, the disclosed systems provide the final set of digital annotations for utilization in training a machine learning model to generate annotations for electronic documents.

公开(公告)号：US11755570B2

公开(公告)日：2023-09-12

申请号：US17116640

申请日：2020-12-09

申请人： ADOBE INC.

发明人： Quan Tran ,  Walter Chang ,  Franck Dernoncourt

IPC分类号： G06F7/00 ,  G06F16/242 ,  G06F40/40 ,  H04L51/02 ,  G06N3/08

CPC分类号： G06F16/243 ,  G06F40/40 ,  G06N3/08 ,  H04L51/02

摘要： The present disclosure provides a memory-based neural network for question answering. Embodiments of the disclosure identify meta-evidence nodes in an embedding space, where the meta-evidence nodes represent salient features of a training set. Each element of the training set may include a questions appended to a ground truth answer. The training set may also include questions with wrong answers that are indicated as such. In some examples, a neural Turing machine (NTM) reads a dataset and summarizes the dataset into a few meta-evidence nodes. A subsequent question may be appended to multiple candidate answers to form an input phrase, which may also be embedded in the embedding space. Then, corresponding weights may be identified for each of the meta-evidence nodes. The embedded input phrase and the weighted meta-evidence nodes may be used to identify the most appropriate answer.

公开(公告)号：US11594077B2

公开(公告)日：2023-02-28

申请号：US17025477

申请日：2020-09-18

申请人： Adobe Inc.

发明人： Trung Bui ,  Zhe Lin ,  Walter Chang ,  Nham Le ,  Franck Dernoncourt

IPC分类号： G06V40/20 ,  G06N3/04 ,  G10L15/26 ,  G10L15/25

摘要： The present disclosure relates to systems, methods, and non-transitory computer readable media for generating modified digital images based on verbal and/or gesture input by utilizing a natural language processing neural network and one or more computer vision neural networks. The disclosed systems can receive verbal input together with gesture input. The disclosed systems can further utilize a natural language processing neural network to generate a verbal command based on verbal input. The disclosed systems can select a particular computer vision neural network based on the verbal input and/or the gesture input. The disclosed systems can apply the selected computer vision neural network to identify pixels within a digital image that correspond to an object indicated by the verbal input and/or gesture input. Utilizing the identified pixels, the disclosed systems can generate a modified digital image by performing one or more editing actions indicated by the verbal input and/or gesture input.

公开(公告)号：US20220318505A1

公开(公告)日：2022-10-06

申请号：US17223166

申请日：2021-04-06

申请人： ADOBE INC.

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

IPC分类号： G06F40/284 ,  G06F40/211 ,  G06F40/30 ,  G06F40/126 ,  G06N3/04 ,  G06N3/08

摘要： 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.