Inventor

MARK EDWARD JOHNSON

Inventor
AU

Overview

65→
Patents
2022–2026
Patent span
Physics
Primary field (CPC G)

Patents· 65 as inventor

Public. Assignee & technology derived from the patent record. Each patent links to its LexDana page.

G06Fprimary
G06FElectric digital data processing40%
G06NComputing arrangements based on specific computational models28%
G10LSpeech analysis techniques or speech synthesis17%
H04LTransmission of digital information, e.g. telegraphic communication13%
G06VImage or video recognition or understanding2%
PatentTitleYear
12,579,447Techniques for two-stage entity-aware data augmentation202612,579,448Techniques for positive entity aware augmentation using two-stage augmentation202612,579,137Output interpretation for a meaning representation language system202612,579,471Data augmentation and batch balancing methods to enhance negation and fairness202612,572,852Lexical dropout for natural language processing202612,572,755System and method for augmenting training data for natural language to meaning representation language systems202612,566,921Gazetteer integration for neural named entity recognition202612,554,929Techniques for using named entity recognition to resolve entity expression in transforming natural language to a meaning representation language202612,554,934Multi-task model with context masking202612,541,672Addressing catastrophic forgetting and over-generalization while training a natural language to a meaning representation language system202612,530,349Techniques for augmenting training data for aggregation and sorting database operations in a natural language to database query system202612,530,545Data augmentation and batch balancing for training multi-lingual model202612,518,098Fusion of word embeddings and word scores for text classification202612,518,129Method and system for over-prediction in neural networks202612,518,111Automating large-scale data collection202612,512,091Fine-tuning multi-head network from a single transformer layer of pre-trained language model202512,511,492Enhanced logits for natural language processing202512,482,457Using a generative adversarial network to train a semantic parser of a dialog system202512,475,325Model robustness on operators and triggering keywords in natural language to a meaning representation language system202512,430,329Transforming natural language to structured query language based on multi- task learning and joint training202512,430,330Calibrating confidence scores of a machine learning model trained as a natural language interface202512,423,530Training data generation to facilitate fine-tuning embedding models202512,412,034Transforming natural language to structured query language based on scalable search and content-based schema linking202512,412,563Path dropout for natural language processing202512,412,126Data augmentation and batch balancing methods to enhance negation and fairness202512,405,975Method and system for constraint based hyperparameter tuning202512,374,322Adjusting outlier data points for training a machine-learning model202512,367,352Deep learning techniques for extraction of embedded data from documents202512,361,219Context tag integration with named entity recognition models202512,340,172Semantic parser including a coarse semantic parser and a fine semantic parser202512,307,336Data manufacturing frameworks for synthesizing synthetic training data to facilitate training a natural language to logical form model202512,299,402Techniques for out-of-domain (OOD) detection202512,293,155Out-of-domain data augmentation for natural language processing202512,288,550Framework for focused training of language models and techniques for end-to-end hypertuning of the framework202512,236,321Batching techniques for handling unbalanced training data for a chatbot202512,223,276Automatic out of scope transition for chatbot202512,217,497Extracting key information from document using trained machine-learning models202512,210,842Distance-based logit value for natural language processing202512,210,973Compressing neural networks for natural language understanding202512,210,830System and techniques for handling long text for pre-trained language models202512,153,881Keyword data augmentation tool for natural language processing202412,153,885Multi-feature balancing for natural language processors202412,099,816Multi-factor modelling for natural language processing202412,026,468Out-of-domain data augmentation for natural language processing202412,019,994Distance-based logit value for natural language processing202412,014,146Techniques for out-of-domain (OOD) detection202411,972,220Enhanced logits for natural language processing202411,972,755Noise data augmentation for natural language processing202411,922,123Automatic out of scope transition for chatbot202411,914,962Reduced training intent recognition techniques202411,908,460Using a generative adversarial network to train a semantic parser of a dialog system202411,868,727Context tag integration with named entity recognition models202411,810,553Using backpropagation to train a dialog system202311,804,219Entity level data augmentation in chatbots for robust named entity recognition202311,790,901Task-oriented dialog suitable for a standalone device202311,763,092Techniques for out-of-domain (OOD) detection202311,651,768Stop word data augmentation for natural language processing202311,574,636Task-oriented dialog suitable for a standalone device202311,551,676Techniques for dialog processing using contextual data202311,538,457Noise data augmentation for natural language processing202211,514,911Reduced training for dialog systems using a database202211,508,359Using backpropagation to train a dialog system202211,501,065Semantic parser including a coarse semantic parser and a fine semantic parser202211,462,208Implementing a correction model to reduce propagation of automatic speech recognition errors202211,403,462Streamlining dialog processing using integrated shared resources2022

Career & activity timeline

Assembled from patent assignee/location history and declaration credentials.

2022–2026Patents assigned to ORACLE INT CORP (65)· patent assignee history
2022–2026Based in AU· patent location history

Inventor activity

Assignee and location history derived from the patent record.

Assignees
AssigneePatentsSpan
ORACLE INT CORP652022–2026
Locations
LocationPatentsSpan
AU652022–2026