Patents by Inventor Vu HOANG
Vu HOANG has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 12361219Abstract: Techniques are provided for using context tags in named-entity recognition (NER) models. In one particular aspect, a method is provided that includes receiving an utterance, generating embeddings for words of the utterance, generating a regular expression and gazetteer feature vector for the utterance, generating a context tag distribution feature vector for the utterance, concatenating or interpolating the embeddings with the regular expression and gazetteer feature vector and the context tag distribution feature vector to generate a set of feature vectors, generating an encoded form of the utterance based on the set of feature vectors, generating log-probabilities based on the encoded form of the utterance, and identifying one or more constraints for the utterance.Type: GrantFiled: November 28, 2023Date of Patent: July 15, 2025Assignee: Oracle International CorporationInventors: Duy Vu, Tuyen Quang Pham, Cong Duy Vu Hoang, Srinivasa Phani Kumar Gadde, Thanh Long Duong, Mark Edward Johnson, Vishal Vishnoi
-
Publication number: 20250225129Abstract: Techniques for natural language processing include accessing an input string comprising a natural language utterance and a database schema representation for a database; providing the natural language utterance to a first encoder to generate one or more embeddings of the natural language utterance; providing the database schema representation to the first encoder to generate one or more embeddings of the database schema representation; encoding, by a second encoder, relations between elements in the database schema representation and words in the natural language utterance based on the one or more embeddings of the natural language utterance and the one or more embeddings of the database schema representation; and generating a logical form for the natural language utterance based on the encoded relations, the one or more embeddings of the natural language utterance, and the one or more embeddings of the database schema representation.Type: ApplicationFiled: January 10, 2024Publication date: July 10, 2025Applicant: Oracle International CorporationInventors: Cong Duy Vu Hoang, Poorya Zaremoodi, Thanh Tien Vu, Gioacchino Tangari, Mark Edward Johnson, Thanh Long Duong, Vishal Vishnoi
-
Publication number: 20250225342Abstract: Techniques are disclosed herein for resolving date/time expressions while transforming natural language to a logical form such as a meaning representation language. A class label for a token in a natural language utterance and a meaning representation for the natural language utterance can be predicted. The class label can be associated with a date/time expression. The meaning representation can include an operator and a value. When the value associated with the class label matches a predetermined value type or the operator matches a predetermined operator, the value and/or the operator can be modified, and an executable statement can be generated for the meaning representation. A query on a computing system can be executed using the executable statement.Type: ApplicationFiled: January 10, 2024Publication date: July 10, 2025Applicant: Oracle International CorporationInventors: Aashna Devang Kanuga, Cong Duy Vu Hoang, Mark Edward Johnson, Vasisht Raghavendra, Yuanxu Wu, Steve Wai-Chun Siu, Nikita Mathur, Gioacchino Tangari, Shubham Pawankumar Shah, Vanshika Sridharan, Thanh Long Duong, Zikai Li, Diego Andres Cornejo Barra, Stephen Andrew McRitchie, Christopher Mark Broadbent, Vishal Vishnoi, Srinivasa Phani Kumar Gadde, Poorya Zaremoodi, Arash Shamaei, Thanh Tien Vu, Yakupitiyage Don Thanuja Samodhye Dharmasiri
-
Publication number: 20250218428Abstract: Techniques are disclosed herein for focused training of language models and end-to-end hypertuning of the framework. In one aspect, a method is provided that includes obtaining a machine learning model pre-trained for language modeling, and post-training the machine learning model for various tasks to generate a focused machine learning model. The post-training includes: (i) training the machine learning model on an unlabeled set of training data pertaining to a task that the machine learning model was pre-trained for as part of the language modeling, and the unlabeled set of training data is obtained with respect to a target domain, a target task, or a target language, and (ii) training the machine learning model on a labeled set of training data that pertains to another task that is an auxiliary task related to a downstream task to be performed using the machine learning model or output from the machine learning model.Type: ApplicationFiled: March 20, 2025Publication date: July 3, 2025Applicant: Oracle International CorporationInventors: Poorya Zaremoodi, Cong Duy Vu Hoang, Duy Vu, Dai Hoang Tran, Budhaditya Saha, Nagaraj N. Bhat, Thanh Tien Vu, Tuyen Quang Pham, Adam Craig Pocock, Katherine Silverstein, Srinivasa Phani Kumar Gadde, Vishal Vishnoi, Mark Edward Johnson, Thanh Long Duong
-
Publication number: 20250190710Abstract: Techniques for augmenting training data include accessing training data comprising a plurality of training examples comprising a first training example comprising a first natural language utterance and a first logical form for the first natural language utterance. A second natural language utterance is generated by adding or replacing one or more values in the first natural language utterance. A logical form for the second natural language utterance is generated. A second training example is generated, comprising the second natural language utterance and the logical form for the second natural language utterance. The training data is augmented by adding the second training example to the plurality of training examples to generate an augmented training data set. A machine learning model is trained to generate logical forms for utterances using the augmented training data set.Type: ApplicationFiled: December 6, 2023Publication date: June 12, 2025Applicant: Oracle International CorporationInventors: Philip Arthur, Gioacchino Tangari, Nitika Mathur, Aashna Devang Kanuga, Cong Duy Vu Hoang, Poorya Zaremoodi, Thanh Long Duong, Mark Edward Johnson
-
Publication number: 20250156649Abstract: Techniques are disclosed herein for improving model robustness on operators and triggering keywords in natural language to a meaning representation language system. The techniques include augmenting an original set of training data for a target robustness bucket by leveraging a combination of two training data generation techniques: (1) modification of existing training examples and (2) synthetic template-based example generation. The resulting set of augmented data examples from the two training data generation techniques are appended to the original set of training data to generate an augmented training data set and the augmented training data set is used to train a machine learning model to generate logical forms for utterances.Type: ApplicationFiled: November 9, 2023Publication date: May 15, 2025Applicant: Oracle International CorporationInventors: Gioacchino Tangari, Chang Xu, Nitika Mathur, Philip Arthur, Syed Najam Abbas Zaidi, Aashna Devang Kanuga, Cong Duy Vu Hoang, Poorya Zaremoodi, Thanh Long Duong, Mark Edward Johnson, Vishal Vishnoi
-
Patent number: 12299402Abstract: The present disclosure relates to techniques for identifying out-of-domain utterances.Type: GrantFiled: May 9, 2024Date of Patent: May 13, 2025Assignee: Oracle International CorporationInventors: Thanh Long Duong, Mark Edward Johnson, Vishal Vishnoi, Crystal C. Pan, Vladislav Blinov, Cong Duy Vu Hoang, Elias Luqman Jalaluddin, Duy Vu, Balakota Srinivas Vinnakota
-
Patent number: 12288550Abstract: Techniques are disclosed herein for focused training of language models and end-to-end hypertuning of the framework. In one aspect, a method is provided that includes obtaining a machine learning model pre-trained for language modeling, and post-training the machine learning model for various tasks to generate a focused machine learning model. The post-training includes: (i) training the machine learning model on an unlabeled set of training data pertaining to a task that the machine learning model was pre-trained for as part of the language modeling, and the unlabeled set of training data is obtained with respect to a target domain, a target task, or a target language, and (ii) training the machine learning model on a labeled set of training data that pertains to another task that is an auxiliary task related to a downstream task to be performed using the machine learning model or output from the machine learning model.Type: GrantFiled: September 23, 2022Date of Patent: April 29, 2025Assignee: ORACLE INTERNATIONAL CORPORATIONInventors: Poorya Zaremoodi, Cong Duy Vu Hoang, Duy Vu, Dai Hoang Tran, Budhaditya Saha, Nagaraj N. Bhat, Thanh Tien Vu, Tuyen Quang Pham, Adam Craig Pocock, Katherine Silverstein, Srinivasa Phani Kumar Gadde, Vishal Vishnoi, Mark Edward Johnson, Thanh Long Duong
-
Patent number: 12280864Abstract: A door assembly for a seat unit provided within a vehicle cabin, in particular an aircraft cabin, the door assembly comprising at least a fixed base structure, a door element movably mounted on the base structure and which is movable between a fully retracted position and at least one deployed position, and a door slide device provided between the base structure and the door element to movably support the door element on the base structure. Further, the door slide device comprises at least a slide carrier bracket fixed to the base structure or the door element, at least one slide unit which is coupled to the slide carrier bracket in a normal operation mode, and at least one separate auxiliary slide arrangement.Type: GrantFiled: July 14, 2023Date of Patent: April 22, 2025Assignee: Adient Aerospace, LLCInventors: Timothy Scotford, Kyle Bettenhausen, Paul Morgan, Matthew Vu Hoang
-
Publication number: 20250117585Abstract: In some aspects, a computing device may receive, at a data processing system, a set of utterances for training or inferencing with a named entity recognizer to assign a label to each token piece from the set of utterances. The computing device may determine a length of each utterance in the set and when the length of the utterance exceeds a pre-determined threshold of token pieces: dividing the utterance into a plurality of overlapping chunks of token pieces; assigning a label together with a confidence score for each token piece in a chunk; determining a final label and an associated confidence score for each chunk of token pieces by merging two confidence scores; determining a final annotated label for the utterance based at least on the merging the two confidence scores; and storing the final annotated label in a memory.Type: ApplicationFiled: December 19, 2024Publication date: April 10, 2025Applicant: Oracle International CorporationInventors: Thanh Tien Vu, Tuyen Quang Pham, Mark Edward Johnson, Thanh Long Duong, Ying Xu, Poorya Zaremoodi, Omid Mohamad Nezami, Budhaditya Saha, Cong Duy Vu Hoang
-
Publication number: 20250117591Abstract: Techniques for using logit values for classifying utterances and messages input to chatbot systems in natural language processing. A method can include a chatbot system receiving an utterance generated by a user interacting with the chatbot system. The chatbot system can input the utterance into a machine-learning model including a set of binary classifiers. Each binary classifier of the set of binary classifiers can be associated with a modified logit function. The method can also include the machine-learning model using the modified logit function to generate a set of distance-based logit values for the utterance. The method can also include the machine-learning model applying an enhanced activation function to the set of distance-based logit values to generate a predicted output. The method can also include the chatbot system classifying, based on the predicted output, the utterance as being associated with the particular class.Type: ApplicationFiled: December 19, 2024Publication date: April 10, 2025Applicant: Oracle International CorporationInventors: Ying XU, Poorya Zaremoodi, Thanh Tien Vu, Cong Duy Vu Hoang, Vladislav Blinov, Yu-Heng Hong, Yakupitiyage Don Thanuja Samodhye Dharmasiri, Vishal Vishnoi, Elias Luqman Jalaluddin, Manish Parekh, Thanh Long Duong, Mark Edward Johnson
-
Publication number: 20250095635Abstract: Techniques are disclosed herein for managing ambiguous date mentions in natural language utterances in transforming natural language utterances to logical forms by encoding the uncertainties of the ambiguous date mentions and including the encoded uncertainties in the logical forms. In a training phase, training examples including natural language utterances, logical forms, and database schema information are automatically augmented and used to train a machine learning model to convert natural language utterances to logical form. In an inference phase, input database schema information is augmented and used by the trained machine learning model to convert an input natural language utterance to logical form.Type: ApplicationFiled: May 6, 2024Publication date: March 20, 2025Applicant: Oracle International CorporationInventors: Gioacchino Tangari, Cong Duy Vu Hoang, Stephen Andrew McRitchie, Steve Wai-Chun Siu, Dalu Guo, Christopher Mark Broadbent, Thanh Long Duong, Srinivasa Phani Kumar Gadde, Vishal Vishnoi, Kenneth Khiaw Hong Eng, Chandan Basavaraju
-
Publication number: 20250094737Abstract: Techniques are disclosed herein for managing date-time intervals in transforming natural language utterances to logical forms by providing an enhanced grammar, a natural language utterance comprising a date-time interval, and database schema information to a machine learning model that has been trained to convert natural language utterances to logical forms; and using the machine learning model to convert the natural language utterance to an output logical form, wherein the output logical form comprises at least one of the date-time interval and an extraction function for extracting date-time information corresponding to the date-time interval from at least one date-time attribute of the database schema information.Type: ApplicationFiled: August 5, 2024Publication date: March 20, 2025Applicant: Oracle International CorporationInventors: Gioacchino Tangari, Cong Duy Vu Hoang, Dalu Guo, Steve Wai-Chun Siu, Stephen Andrew McRitchie, Christopher Mark Broadbent, Thanh Long Duong, Srinivasa Phani Kumar Gadde, Vishal Vishnoi, Chandan Basavaraju, Kenneth Khiaw Hong Eng
-
Publication number: 20250068627Abstract: Techniques are disclosed herein for transforming natural language conversations into a visual output. In one aspect, a computer-implement method includes generating an input string by concatenating a natural language utterance with a schema representation comprising a set of entities for visualization actions, generating, by a first encoder of a machine learning model, one or more embeddings of the input string, encoding, by a second encoder of the machine learning model, relations between elements in the schema representation and words in the natural language utterance based on the one or more embeddings, generating, by a grammar-based decoder of the machine learning model and based on the encoded relations and the one or more embeddings, an intermediate logical form that represents at least the query, the one or more visualization actions, or the combination thereof, and generating, based on the intermediate logical form, a command for a computing system.Type: ApplicationFiled: March 26, 2024Publication date: February 27, 2025Applicant: Oracle International CorporationInventors: Cong Duy Vu Hoang, Gioacchino Tangari, Stephen Andrew McRitchie, Nitika Mathur, Aashna Devang Kanuga, Steve Wai-Chun Siu, Dalu Guo, Chang Xu, Mark Edward Johnson, Christopher Mark Broadbent, Thanh Long Duong, Srinivasa Phani Kumar Gadde, Vishal Vishnoi, Chandan Basavaraju, Kenneth Khiaw Hong Eng
-
Publication number: 20250068626Abstract: The present disclosure relates to manufacturing training data by leveraging an automated pipeline that manufactures visualization training datasets to train a machine learning model to convert a natural language utterance into meaning representation language logical form that includes one or more visualization actions. Aspects are directed towards accessing an original training dataset, a visualization query dataset, an incremental visualization dataset, a manipulation visualization dataset, or any combination thereof. One or more visualization training datasets are generated by: (i) modifying examples in the original training dataset, the visualization query dataset, or both to include visualization actions, (ii) generating examples, using the incremental visualization dataset, the manipulation visualization dataset, or both, that include visualization actions, or (iii) both (i) and (ii).Type: ApplicationFiled: March 1, 2024Publication date: February 27, 2025Applicant: Oracle International CorporationInventors: Gioacchino Tangari, Steve Wai-Chun Siu, Dalu Guo, Cong Duy Vu Hoang, Berk Sarioz, Chang Xu, Stephen Andrew McRitchie, Mark Edward Johnson, Christopher Mark Broadbent, Thanh Long Duong, Srinivasa Phani Kumar Gadde, Vishal Vishnoi, Chandan Basavaraju, Kenneth Khiaw Hong Eng
-
Patent number: 12224509Abstract: Reconfigurable antenna systems with ground tuning pads are provided herein. In certain embodiments, a radio frequency module includes a module substrate including a first conductive layer and a second conductive layer separated by dielectric, an antenna element formed in the first conductive layer, a plurality of tuning conductors formed in the first conductive layer, a first ground tuning pad formed in the second conductive layer and receiving a ground voltage, and a first switch. The tuning conductors include a first tuning conductor spaced apart from the antenna element on a first side of the antenna element and a second tuning conductor spaced apart from the antenna element on a second side of the antenna element. The first switch is electrically connected between the first tuning conductor and the first ground tuning pad and selectively connects the first tuning conductor to the first ground tuning pad to tune the antenna element.Type: GrantFiled: March 27, 2024Date of Patent: February 11, 2025Assignee: Skyworks Solutions, Inc.Inventors: René RodrÃguez, Dinhphuoc Vu Hoang, Hardik Bhupendra Modi
-
Patent number: 12210830Abstract: In some aspects, a computing device may receive, at a data processing system, a set of utterances for training or inferencing with a named entity recognizer to assign a label to each token piece from the set of utterances. The computing device may determine a length of each utterance in the set and when the length of the utterance exceeds a pre-determined threshold of token pieces: dividing the utterance into a plurality of overlapping chunks of token pieces; assigning a label together with a confidence score for each token piece in a chunk; determining a final label and an associated confidence score for each chunk of token pieces by merging two confidence scores; determining a final annotated label for the utterance based at least on the merging the two confidence scores; and storing the final annotated label in a memory.Type: GrantFiled: May 20, 2022Date of Patent: January 28, 2025Assignee: Oracle International CorporationInventors: Thanh Tien Vu, Tuyen Quang Pham, Mark Edward Johnson, Thanh Long Duong, Ying Xu, Poorya Zaremoodi, Omid Mohamad Nezami, Budhaditya Saha, Cong Duy Vu Hoang
-
Patent number: 12210842Abstract: Techniques for using logit values for classifying utterances and messages input to chatbot systems in natural language processing. A method can include a chatbot system receiving an utterance generated by a user interacting with the chatbot system. The chatbot system can input the utterance into a machine-learning model including a set of binary classifiers. Each binary classifier of the set of binary classifiers can be associated with a modified logit function. The method can also include the machine-learning model using the modified logit function to generate a set of distance-based logit values for the utterance. The method can also include the machine-learning model applying an enhanced activation function to the set of distance-based logit values to generate a predicted output. The method can also include the chatbot system classifying, based on the predicted output, the utterance as being associated with the particular class.Type: GrantFiled: December 19, 2023Date of Patent: January 28, 2025Assignee: Oracle International CorporationInventors: Ying Xu, Poorya Zaremoodi, Thanh Tien Vu, Cong Duy Vu Hoang, Vladislav Blinov, Yu-Heng Hong, Yakupitiyage Don Thanuja Samodhye Dharmasiri, Vishal Vishnoi, Elias Luqman Jalaluddin, Manish Parekh, Thanh Long Duong, Mark Edward Johnson
-
Patent number: 12191013Abstract: The invention provides a radiology report editing method and system.Type: GrantFiled: September 1, 2022Date of Patent: January 7, 2025Assignee: VINBRAIN JOINT STOCK COMPANYInventors: Manh Hung Nguyen, Vu Hoang, Anh Tu Nguyen, Steven Quoc Hung Truong, Huu Trung Bui
-
Publication number: 20240419910Abstract: A method includes receiving an indication of a first coverage value corresponding to a desired overlap between a dataset of natural language phrases and a training dataset for training a machine learning model; determining a second coverage value corresponding to a measured overlap between the dataset of natural language phrases and the training dataset; determining a coverage delta value based on a comparison between the first coverage value and the second coverage value; modifying, based on the coverage delta value, the dataset of natural language phrases; and processing, utilizing a machine learning model including the modified dataset of natural language phrases, an input dataset including a set of input features. The machine learning model processes the input dataset based at least in part on the dataset of natural language phrases to generate an output dataset.Type: ApplicationFiled: August 29, 2024Publication date: December 19, 2024Applicant: Oracle International CorporationInventors: Thanh Long Duong, Vishal Vishnoi, Mark Edward Johnson, Elias Luqman Jalaluddin, Tuyen Quang Pham, Cong Duy Vu Hoang, Poorya Zaremoodi, Srinivasa Phani Kumar Gadde, Aashna Devang Kanuga, Zikai Li, Yuanxu Wu