-
公开(公告)号：US11537950B2
公开(公告)日：2022-12-27
申请号：US17070568
申请日：2020-10-14
Applicant: Adobe Inc.
Inventor： Trung Bui , Tuan Manh Lai , Quan Tran , Doo Soon Kim
IPC: G06N20/00 , G06F16/248
Abstract: This disclosure describes one or more implementations of a text sequence labeling system that accurately and efficiently utilize a joint-learning self-distillation approach to improve text sequence labeling machine-learning models. For example, in various implementations, the text sequence labeling system trains a text sequence labeling machine-learning teacher model to generate text sequence labels. The text sequence labeling system then creates and trains a text sequence labeling machine-learning student model utilizing the training and the output of the teacher model. Upon the student model achieving improved results over the teacher model, the text sequence labeling system re-initializes the teacher model with the learned model parameters of the student model and repeats the above joint-learning self-distillation framework. The text sequence labeling system then utilizes a trained text sequence labeling model to generate text sequence labels from input documents.
-
公开(公告)号：US20220114476A1
公开(公告)日：2022-04-14
申请号：US17070568
申请日：2020-10-14
Applicant: Adobe Inc.
Inventor： Trung Bui , Tuan Manh Lai , Quan Tran , Doo Soon Kim
IPC: G06N20/00 , G06F16/248
Abstract: This disclosure describes one or more implementations of a text sequence labeling system that accurately and efficiently utilize a joint-learning self-distillation approach to improve text sequence labeling machine-learning models. For example, in various implementations, the text sequence labeling system trains a text sequence labeling machine-learning teacher model to generate text sequence labels. The text sequence labeling system then creates and trains a text sequence labeling machine-learning student model utilizing the training and the output of the teacher model. Upon the student model achieving improved results over the teacher model, the text sequence labeling system re-initializes the teacher model with the learned model parameters of the student model and repeats the above joint-learning self-distillation framework. The text sequence labeling system then utilizes a trained text sequence labeling model to generate text sequence labels from input documents.
-
3.发明公开公开(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
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：US20210182662A1
公开(公告)日：2021-06-17
申请号：US16717698
申请日：2019-12-17
Applicant: Adobe Inc.
Inventor： Tuan Manh Lai , Trung Huu Bui , Quan Hung Tran
IPC: G06N3/08 , G06N3/04 , G06F40/284
Abstract: Techniques for training a first neural network (NN) model using a pre-trained second NN model are disclosed. In an example, training data is input to the first and second models. The training data includes masked tokens and unmasked tokens. In response, the first model generates a first prediction associated with a masked token and a second prediction associated with an unmasked token, and the second model generates a third prediction associated with the masked token and a fourth prediction associated with the unmasked token. The first model is trained, based at least in part on the first, second, third, and fourth predictions. In another example, a prediction associated with a masked token, a prediction associated with an unmasked token, and a prediction associated with whether two sentences of training data are adjacent sentences are received from each of the first and second models. The first model is trained using the predictions.
-
5.发明申请公开(公告)号：US20190325068A1
公开(公告)日：2019-10-24
申请号：US15957556
申请日：2018-04-19
Applicant: Adobe Inc.
Inventor： Tuan Manh Lai , Trung Bui , Sheng Li , Quan Hung Tran , Hung Bui
Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating digital responses to digital queries by utilizing a classification model and query-specific analysis models. For example, the disclosed systems can train a classification model to generate query classifications corresponding to product queries, conversational queries, and/or recommendation/purchase queries. Moreover, the disclosed systems can apply the classification model to select pertinent models for particular queries. For example, upon classifying a product query, disclosed systems can utilize a neural ranking model (trained based on a set of training product specifications and training queries) to generate relevance scores for product specifications associated with a digital query. The disclosed systems can further compare generated relevance scores to select a product specification and generate a digital response that includes the pertinent product specification to provide for display to a client device.
-
Patent Agency Ranking
公开(公告)号：US11776036B2
公开(公告)日：2023-10-03
申请号：US15957556
申请日：2018-04-19
Applicant: Adobe Inc.
Inventor： Tuan Manh Lai , Trung Bui , Sheng Li , Quan Hung Tran , Hung Bui
IPC: G06Q30/0601 , G06N3/08 , G06F16/951 , G06F16/583 , G06V10/764
CPC classification number: G06Q30/0631 , G06F16/583 , G06F16/951 , G06N3/08 , G06V10/764
Abstract: The present description relates to systems, methods, and non-transitory computer readable media for generating digital responses to digital queries by utilizing a classification model and query-specific analysis models. For example, the described systems can train a classification model to generate query classifications corresponding to product queries, conversational queries, and/or recommendation/purchase queries. Moreover, the described systems can apply the classification model to select pertinent models for particular queries. For example, upon classifying a product query, the described systems can utilize a neural ranking model (trained based on a set of training product specifications and training queries) to generate relevance scores for product specifications associated with a digital query. The described systems can further compare generated relevance scores to select a product specification and generate a digital response that includes the pertinent product specification to provide for display to a client device.
-
7.发明授权公开(公告)号：US11610584B2
公开(公告)日：2023-03-21
申请号：US16889669
申请日：2020-06-01
Applicant: Adobe Inc.
Inventor： Tuan Manh Lai , Trung Bui , Quan Hung Tran
IPC: G10L15/00 , G10L15/22 , G10L15/02 , G10L15/183 , G10L15/18
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.
-
8.发明申请公开(公告)号：US20220383150A1
公开(公告)日：2022-12-01
申请号：US17331131
申请日：2021-05-26
Applicant: Adobe Inc.
Inventor： Nham Van Le , Tuan Manh Lai , Trung Bui , Doo Soon Kim
Abstract: This disclosure describes methods, non-transitory computer readable storage media, and systems that provide a platform for on-demand selection of machine-learning models and on-demand learning of parameters for the selected machine-learning models via cloud-based systems. For instance, the disclosed system receives a request indicating a selection of a machine-learning model to perform a machine-learning task (e.g., a natural language task) utilizing a specific dataset (e.g., a user-defined dataset). The disclosed system utilizes a scheduler to monitor available computing devices on cloud-based storage systems for instantiating the selected machine-learning model. Using the indicated dataset at a determined cloud-based computing device, the disclosed system automatically trains the machine-learning model. In additional embodiments, the disclosed system generates a dataset visualization, such as an interactive confusion matrix, for interactively viewing and selecting data generated by the machine-learning model.
-
公开(公告)号：US20230403175A1
公开(公告)日：2023-12-14
申请号：US17806751
申请日：2022-06-14
Applicant: ADOBE INC.
Inventor： Tuan Manh Lai , Trung Huu Bui , Doo Soon Kim
IPC: H04L12/18 , G06F40/284 , G06N3/04
CPC classification number: H04L12/1831 , G06F40/284 , G06N3/04
Abstract: Systems and methods for coreference resolution are provided. One aspect of the systems and methods includes inserting a speaker tag into a transcript, wherein the speaker tag indicates that a name in the transcript corresponds to a speaker of a portion of the transcript; encoding a plurality of candidate spans from the transcript based at least in part on the speaker tag to obtain a plurality of span vectors; extracting a plurality of entity mentions from the transcript based on the plurality of span vectors, wherein each of the plurality of entity mentions corresponds to one of the plurality of candidate spans; and generating coreference information for the transcript based on the plurality of entity mentions, wherein the coreference information indicates that a pair of candidate spans of the plurality of candidate spans corresponds to a pair of entity mentions that refer to a same entity.
-
10.发明授权公开(公告)号：US11651211B2
公开(公告)日：2023-05-16
申请号：US16717698
申请日：2019-12-17
Applicant: Adobe Inc.
Inventor： Tuan Manh Lai , Trung Huu Bui , Quan Hung Tran
CPC classification number: G06N3/08 , G06F40/284 , G06N3/045 , G10L15/16 , G10L25/30
Abstract: Techniques for training a first neural network (NN) model using a pre-trained second NN model are disclosed. In an example, training data is input to the first and second models. The training data includes masked tokens and unmasked tokens. In response, the first model generates a first prediction associated with a masked token and a second prediction associated with an unmasked token, and the second model generates a third prediction associated with the masked token and a fourth prediction associated with the unmasked token. The first model is trained, based at least in part on the first, second, third, and fourth predictions. In another example, a prediction associated with a masked token, a prediction associated with an unmasked token, and a prediction associated with whether two sentences of training data are adjacent sentences are received from each of the first and second models. The first model is trained using the predictions.
-
-
-
-
-
-
-
-
-
Search Results
12
records
(took 0.013 seconds)
