Patents by Inventor Quang Pham
Quang Pham 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).
-
Publication number: 20240111619Abstract: Systems and methods related to serial communication devices are provided. An example integrated circuit (IC) device includes interface circuitry coupled to a two-wire serial communication bus having a serial clock (SCL) line and a serial data (SDA) bus line. The IC device further includes bus stuck recovery circuitry to monitor for a local SDA fault condition at the IC device based on a number of clock cycles during which an internal SDA signal (e.g., generated by the IC device) drives the SDA bus line to a first signal state, the clock cycles based on a clock signal received from the SCL line; and responsive to the local SDA fault condition, release the SDA bus line independent of the internal SDA signal, where the SDA bus line is in a second signal state different from the first signal state based on the release.Type: ApplicationFiled: September 30, 2022Publication date: April 4, 2024Applicant: Analog Devices, Inc.Inventors: Ran TAO, Johan H. MANSSON, Khiem Quang NGUYEN, Long Thanh PHAM, Shane P. KEATING
-
Publication number: 20240095454Abstract: 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: ApplicationFiled: November 28, 2023Publication date: March 21, 2024Applicant: 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: 20240062011Abstract: Techniques are disclosed herein for using named entity recognition to resolve entity expression while transforming natural language to a meaning representation language. In one aspect, a method includes accessing natural language text, predicting, by a first machine learning model, a class label for a token in the natural language text, predicting, by a second machine-learning model, operators for a meaning representation language and a value or value span for each attribute of the operators, in response to determining that the value or value span for a particular attribute matches the class label, converting a portion of the natural language text for the value or value span into a resolved format, and outputting syntax for the meaning representation language. The syntax comprises the operators with the portion of the natural language text for the value or value span in the resolved format.Type: ApplicationFiled: July 13, 2023Publication date: February 22, 2024Applicant: Oracle International CorporationInventors: Aashna Devang Kanuga, Cong Duy Vu Hoang, Mark Edward Johnson, Vasisht Raghavendra, Yuanxu Wu, Steve Wai-Chun Siu, Nitika Mathur, Gioacchino Tangari, Shubham Pawankumar Shah, Vanshika Sridharan, Zikai Li, Diego Andres Cornejo Barra, Stephen Andrew McRitchie, Christopher Mark Broadbent, Vishal Vishnoi, Srinivasa Phani Kumar Gadde, Poorya Zaremoodi, Thanh Long Duong, Bhagya Gayathri Hettige, Tuyen Quang Pham, Arash Shamaei, Thanh Tien Vu, Yakupitiyage Don Thanuja Samodhve Dharmasiri
-
Publication number: 20240062108Abstract: Techniques are disclosed herein for training and deploying a named entity recognition model. The techniques include implementing a nested labeling scheme for named entities within the training data and then training a machine learning model on the training data The techniques further include extracting an entity hierarchy for a predicted class based on a hierarchical template associated with a composite label, where the predicted class is representative of multiple named entity classes comprising at least a parent class and a child class associated with the composite label. The techniques further include increasing the volume of training data via data mining for sequence tags in a language corpus and then training a machine learning model on the training data.Type: ApplicationFiled: May 25, 2023Publication date: February 22, 2024Applicant: Oracle International CorporationInventors: Tuyen Quang Pham, Bhagya Hettige, Gioacchino Tangari, Yakupitiyage Don Thanuja Samodhye Dharmasiri, Thanh Long Duong
-
Patent number: 11868727Abstract: 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: January 19, 2022Date of Patent: January 9, 2024Assignee: 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: 20230419040Abstract: Novel techniques are described for data augmentation using a two-stage entity-aware augmentation to improve model robustness to entity value changes for intent prediction.Type: ApplicationFiled: February 1, 2023Publication date: December 28, 2023Applicant: Oracle International CorporationInventors: Ahmed Ataallah Ataallah Abobakr, Shivashankar Subramanian, Ying Xu, Vladislav Blinov, Umanga Bista, Tuyen Quang Pham, Thanh Long Duong, Mark Edward Johnson, Elias Luqman Jalaluddin, Vanshika Sridharan, Xin Xu, Srinivasa Phani Kumar Gadde, Vishal Vishnoi
-
Publication number: 20230419052Abstract: Novel techniques are described for positive entity-aware augmentation using a two-stage augmentation to improve the stability of the model to entity value changes for intent prediction. In one particular aspect, a method is provided that includes accessing a first set of training data for an intent prediction model, the first set of training data comprising utterances and intent labels; applying one or more positive data augmentation techniques to the first set of training data, depending on the tuning requirements for hyper-parameters, to result in a second set of training data, where the positive data augmentation techniques comprise Entity-Aware (“EA”) technique and a two-stage augmentation technique; combining the first set of training data and the second set of training data to generate expanded training data; and training the intent prediction model using the expanded training data.Type: ApplicationFiled: February 1, 2023Publication date: December 28, 2023Applicant: Oracle International CorporationInventors: Ahmed Ataallah Ataallah Abobakr, Shivashankar Subramanian, Ying Xu, Vladislav Blinov, Umanga Bista, Tuyen Quang Pham, Thanh Long Duong, Mark Edward Johnson, Elias Luqman Jalaluddin, Vanshika Sridharan, Xin XU, Srinivasa Phani Kumar Gadde, Vishal Vishnoi
-
Publication number: 20230419127Abstract: Novel techniques are described for negative entity-aware augmentation using a two-stage augmentation to improve the stability of the model to entity value changes for intent prediction. In some embodiments, a method comprises accessing a first set of training data for an intent prediction model, the first set of training data comprising utterances and intent labels; applying one or more negative entity-aware data augmentation techniques to the first set of training data, depending on the tuning requirements for hyper-parameters, to result in a second set of training data, where the one or more negative entity-aware data augmentation techniques comprise Keyword Augmentation Technique (“KAT”) plus entity without context technique and KAT plus entity in random context as OOD technique; combining the first set of training data and the second set of training data to generate expanded training data; and training the intent prediction model using the expanded training data.Type: ApplicationFiled: February 1, 2023Publication date: December 28, 2023Applicant: Oracle International CorporationInventors: Ahmed Ataallah Ataallah Abobakr, Shivashankar Subramanian, Ying Xu, Vladislav Blinov, Umanga Bista, Tuyen Quang Pham, Thanh Long Duong, Mark Edward Johnson, Elias Luqman Jalaluddin, Vanshika Sridharan, Xin Xu, Srinivasa Phani Kumar Gadde, Vishal Vishnoi
-
Patent number: 11817584Abstract: The present invention relates to a binder for a lithium secondary battery, an electrode comprising the same, and a lithium secondary battery comprising the electrode. More specifically, the present invention provides a binder for a lithium secondary battery having excellent cycle life and high energy density, an anode for a lithium secondary battery comprising the same, and a lithium secondary battery prepared therefrom.Type: GrantFiled: January 21, 2019Date of Patent: November 14, 2023Assignee: IPI TECH INC.Inventors: Seung Wan Song, Hieu Quang Pham, Hyun Min Jung
-
Patent number: 11790901Abstract: Described herein are dialog systems, and techniques for providing such dialog systems, that are suitable for use on standalone computing devices. In some embodiments, a dialog system includes a dialog manager, which takes as input an input logical form, which may be a representation of user input. The dialog manager may include a dialog state tracker, an execution subsystem, a dialog policy subsystem, and a context stack. The dialog state tracker may generate an intermediate logical form from the input logical form combined with a context from the context stack. The context stack may maintain a history of a current dialog, and thus, the intermediate logical form may include contextual information potentially missing from the input logical form. The execution subsystem may execute the intermediate logical form to produce an execution result, and the dialog policy subsystem may generate an output logical form based on the execution result.Type: GrantFiled: December 30, 2022Date of Patent: October 17, 2023Assignee: Oracle International CorporationInventors: Thanh Long Duong, Mark Edward Johnson, Vu Cong Duy Hoang, Tuyen Quang Pham, Yu-Heng Hong, Vladislavs Dovgalecs, Guy Bashkansky, Jason Eric Black, Andrew David Bleeker, Serge Le Huitouze
-
Publication number: 20230325599Abstract: Techniques are provided for augmenting training data using gazetteers and perturbations to facilitate training named entity recognition models. The training data can be augmented by generating additional utterances from original utterances in the training data and combining the generated additional utterances with the original utterances to form the augmented training data. The additional utterances can be generated by replacing the named entities in the original utterances with different named entities and/or perturbed versions of the named entities in the original utterances selected from a gazetteer. Gazetteers of named entities can be generated from the training data and expanded by searching a knowledge base and/or perturbing the named entities therein. The named entity recognition model can be trained using the augmented training data.Type: ApplicationFiled: March 17, 2023Publication date: October 12, 2023Applicant: Oracle International CorporationInventors: Omid Mohamad Nezami, Shivashankar Subramanian, Thanh Tien Vu, Tuyen Quang Pham, Budhaditya Saha, Aashna Devang Kanuga, Shubham Pawankumar Shah
-
Publication number: 20230244943Abstract: Embodiments provide a framework combining fast and slow learning Networks (referred to as “FSNet”) to train deep neural forecasters on the fly for online time-series fore-casting. FSNet is built on a deep neural network backbone (slow learner) with two complementary components to facilitate fast adaptation to both new and recurrent concepts. To this end, FSNet employs a per-layer adapter to monitor each layer's contribution to the forecasting loss via its partial derivative. The adapter transforms each layer's weight and feature at each step based on its recent gradient, allowing a finegrain per-layer fast adaptation to optimize the current loss. In addition, FSNet employs a second and complementary associative memory component to store important, recurring patterns observed during training. The adapter interacts with the memory to store, update, and retrieve the previous transformations, facilitating fast learning of such patterns.Type: ApplicationFiled: July 22, 2022Publication date: August 3, 2023Inventors: Hong-Quang Pham, Chenghao Liu, Doyen Sahoo, Chu Hong Hoi
-
Publication number: 20230206125Abstract: Techniques are provided for improved training of a machine learning model using lexical dropout. A machine learning model and a training data set are accessed. The training data set can include sample utterances and corresponding labels. A dropout parameter is identified. The dropout parameter can indicate a likelihood for dropping out one or more feature vectors for tokens associated with respective entities during training of the machine learning model. The dropout parameter is applied to feature vectors for tokens associated with respective entities. The machine learning model is trained using the training data set and the dropout parameter to generate a trained machine learning model. The use of the trained the machine learning model is facilitated.Type: ApplicationFiled: December 22, 2022Publication date: June 29, 2023Applicant: Oracle International CorporationInventors: Tuyen Quang Pham, Cong Duy Vu Hoang, Thanh Tien Vu, Mark Edward Johnson, Thanh Long Duong
-
Publication number: 20230205999Abstract: Techniques are provided for named entity recognition using a gazetteer incorporated with a neural network. An utterance is received from a user. The utterance is input into a neural network comprising model parameters learned for named entity recognition. The neural network generates a first representation of one or more named entities based on the utterance. A gazetteer is searched based on the input utterance to generate a second representation of one or more named entities identified in the utterance. The first named entity representation is combined with the second named entity representation to generate a combined named entity representation. The combined named entity representation is output for facilitating a response to the user.Type: ApplicationFiled: December 22, 2022Publication date: June 29, 2023Applicant: Oracle International CorporationInventors: Tuyen Quang Pham, Cong Duy Vu Hoang, Mark Edward Johnson, Thanh Long Duong
-
Publication number: 20230186914Abstract: Described herein are dialog systems, and techniques for providing such dialog systems, that are suitable for use on standalone computing devices. In some embodiments, a dialog system includes a dialog manager, which takes as input an input logical form, which may be a representation of user input. The dialog manager may include a dialog state tracker, an execution subsystem, a dialog policy subsystem, and a context stack. The dialog state tracker may generate an intermediate logical form from the input logical form combined with a context from the context stack. The context stack may maintain a history of a current dialog, and thus, the intermediate logical form may include contextual information potentially missing from the input logical form. The execution subsystem may execute the intermediate logical form to produce an execution result, and the dialog policy subsystem may generate an output logical form based on the execution result.Type: ApplicationFiled: December 30, 2022Publication date: June 15, 2023Applicant: Oracle International CorporationInventors: Thanh Long Duong, Mark Edward Johnson, Vu Cong Duy Hoang, Tuyen Quang Pham, Yu-Heng Hong, Vladislavs Dovgalecs, Guy Bashkansky, Jason Eric Black, Andrew David Bleeker, Serge Le Huitouze
-
Publication number: 20230154455Abstract: Techniques are provided for improved training of a machine-learning model that includes multiple layers and is configured to process textual language input. The machine-learning model includes one or more blocks in which each block includes a multi-head self-attention network, a first connection for providing input to the multi-head self-attention network, and a second (residual) connection for providing the input to a normalization layer, bypassing the multi-head self-attention network. During training, the second connection is dropped out according to a dropout parameter. Additionally, or alternatively, an attention weight matrix is used for dropout by blocking diagonal entries in the attention weight matrix. As a result, the machine-learning model increasingly focuses on contextual information, which provides more accurate language processing results.Type: ApplicationFiled: November 16, 2022Publication date: May 18, 2023Applicant: Oracle International CorporationInventors: Thanh Tien Vu, Tuyen Quang Pham, Mark Edward Johnson, Thanh Long Duong
-
Publication number: 20230136965Abstract: In some aspects, a computer obtains a trained conditional random field (CRF) model comprising a set of model parameters learned from training data and stored in a transition matrix. Tag sequences, inconsistent with the tag sequence logic, are identified for the tags within the transition matrix. setting, within the transition matrix, a cost associated with transitioning between the pair of tags to be equal to a predefined hyperparameter value that penalizes the transitioning between the inconsistent pair of tags. The CRF model receives a string of text comprising one or more named entities. The CRF model inputs the string of text into the CRF model having the cost associated with the transitioning between the pair of tags set equal to the predefined hyperparameter value. The CRF model classifies the words within the string of text into different classes which might include the one or more named entities.Type: ApplicationFiled: October 31, 2022Publication date: May 4, 2023Applicant: Oracle International CorporationInventors: Thanh Tien Vu, Tuyen Quang Pham, Mark Edward Johnson, Thanh Long Duong, Aashna Devang Kanuga, Srinivasa Phani Kumar Gadde, Vishal Vishnoi
-
Publication number: 20230115321Abstract: Techniques are provided for customizing or fine-tuning a pre-trained version of a machine-learning model that includes multiple layers and is configured to process audio or textual language input. Each of the multiple layers is configured with a plurality of layer-specific pre-trained parameter values corresponding to a plurality of parameters, and each of the multiple layers is configured to implement multi-head attention. An incomplete subset of the multiple layers is identified for which corresponding layer-specific pre-trained parameter values are to be fine-tuned using a client data set. The machine-learning model is fine-tuned using the client data set to generate an updated version of the machine-learning model, where the layer-specific pre-trained parameter values configured for each layer of one of more of the multiple layers not included in the incomplete subset are frozen during the fine-tuning. Use of the updated version of the machine-learning model is facilitated.Type: ApplicationFiled: May 3, 2022Publication date: April 13, 2023Applicant: Oracle International CorporationInventors: Thanh Tien Vu, Tuyen Quang Pham, Omid Mohamad Nezami, Mark Edward Johnson, Thanh Long Duong, Cong Duy Vu Hoang
-
Publication number: 20230098783Abstract: 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: September 23, 2022Publication date: March 30, 2023Applicant: 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: 11574636Abstract: Described herein are dialog systems, and techniques for providing such dialog systems, that are suitable for use on standalone computing devices. In some embodiments, a dialog system includes a dialog manager, which takes as input an input logical form, which may be a representation of user input. The dialog, manager may include a dialog state tracker, an execution subsystem, a dialog policy subsystem, and a context stack. The dialog state tracker may generate an intermediate logical form from the input logical form combined with a context from the context stack. The context stack may maintain a history of a current dialog, and thus, the intermediate logical form may include contextual information potentially missing from the input logical form. The execution subsystem may execute the intermediate logical form to produce an execution result, and the dialog policy subsystem may generate an output logical form based on the execution result.Type: GrantFiled: August 28, 2020Date of Patent: February 7, 2023Assignee: Oracle International CorporationInventors: Thanh Long Duong, Mark Edward Johnson, Vu Cong Duy Hoang, Tuyen Quang Pham, Yu-Heng Hong, Vladislavs Dovgalecs, Guy Bashkansky, Jason Eric Black, Andrew David Bleeker, Serge Le Huitouze