Mark Edward Johnson

FUSION OF WORD EMBEDDINGS AND WORD SCORES FOR TEXT CLASSIFICATION

FINE-TUNING MULTI-HEAD NETWORK FROM A SINGLE TRANSFORMER LAYER OF PRE-TRAINED LANGUAGE MODEL

CALIBRATING CONFIDENCE SCORES OF A MACHINE LEARNING MODEL TRAINED AS A NATURAL LANGUAGE INTERFACE

CONTEXT TAG INTEGRATION WITH NAMED ENTITY RECOGNITION MODELS

RESOLVING DATE/TIME EXPRESSION AMBIGUITY IN TRANSFORMING NATURAL LANGUAGE TO A MEANING REPRESENTATION

TECHNIQUES FOR EFFICIENT ENCODING IN NEURAL SEMANTIC PARSING SYSTEMS

FRAMEWORK FOR FOCUSED TRAINING OF LANGUAGE MODELS AND TECHNIQUES FOR END-TO-END HYPERTUNING OF THE FRAMEWORK

SYSTEM AND METHOD FOR AUGMENTING TRAINING DATA FOR NATURAL LANGUAGE TO MEANING REPRESENTATION LANGUAGE SYSTEMS

EXTRACTING KEY INFORMATION FROM DOCUMENT USING TRAINED MACHINE-LEARNING MODELS

MODEL ROBUSTNESS ON OPERATORS AND TRIGGERING KEYWORDS IN NATURAL LANGUAGE TO A MEANING REPRESENTATION LANGUAGE SYSTEM

SYSTEM AND TECHNIQUES FOR HANDLING LONG TEXT FOR PRE-TRAINED LANGUAGE MODELS

DIGITAL ASSISTANT USING GENERATIVE ARTIFICIAL INTELLIGENCE

EXECUTING AN EXECUTION PLAN WITH A DIGITAL ASSISTANT AND USING LARGE LANGUAGE MODELS

TECHNIQUES FOR TRANSFORMING NATURAL LANGUAGE CONVERSATION INTO A VISUALIZATION REPRESENTATION

TECHNIQUES FOR MANUFACTURING TRAINING DATA TO TRANSFORM NATURAL LANGUAGE INTO A VISUALIZATION REPRESENTATION

MULTI-FEATURE BALANCING FOR NATURAL LANGUAGE PROCESSORS

Techniques for out-of-domain (OOD) detection

Out-of-domain data augmentation for natural language processing

ENHANCED LOGITS FOR NATURAL LANGUAGE PROCESSING

OUTPUT INTERPRETATION FOR A MEANING REPRESENTATION LANGUAGE SYSTEM

AUTOMATING LARGE-SCALE DATA COLLECTION

USING A GENERATIVE ADVERSARIAL NETWORK TO TRAIN A SEMANTIC PARSER OF A DIALOG SYSTEM

MULTI-TASK MODEL WITH CONTEXT MASKING

DATA AUGMENTATION AND BATCH BALANCING FOR TRAINING MULTI-LINGUAL MODEL

OUTPUT INTERPRETATION FOR A MEANING REPRESENTATION LANGUAGE SYSTEM

CONVERSATIONAL DOCUMENT QUESTION ANSWERING

OBJECTIVE FUNCTION OPTIMIZATION IN TARGET BASED HYPERPARAMETER TUNING

CONTINUOUS HYPER-PARAMETER TUNING WITH AUTOMATIC DOMAIN WEIGHT ADJUSTMENT BASED ON PERIODIC PERFORMANCE CHECKPOINTS

ADDRESSING CATASTROPHIC FORGETTING AND OVER-GENERALIZATION WHILE TRAINING A NATURAL LANGUAGE TO A MEANING REPRESENTATION LANGUAGE SYSTEM

CALIBRATING CONFIDENCE SCORES OF A MACHINE LEARNING MODEL TRAINED AS A NATURAL LANGUAGE INTERFACE

TECHNIQUES FOR USING NAMED ENTITY RECOGNITION TO RESOLVE ENTITY EXPRESSION IN TRANSFORMING NATURAL LANGUAGE TO A MEANING REPRESENTATION LANGUAGE

SYSTEM AND METHOD OF SELECTIVE FINE-TUNING FOR CUSTOM TRAINING OF A NATURAL LANGUAGE TO LOGICAL FORM MODEL

DETECTING OUT-OF-DOMAIN, OUT-OF-SCOPE, AND CONFUSION-SPAN (OOCS) INPUT FOR A NATURAL LANGUAGE TO LOGICAL FORM MODEL

TECHNIQUES FOR AUGMENTING TRAINING DATA FOR AGGREGATION AND SORTING DATABASE OPERATIONS IN A NATURAL LANGUAGE TO DATABASE QUERY SYSTEM

TECHNIQUES FOR CONVERTING A NATURAL LANGUAGE UTTERANCE TO AN INTERMEDIATE DATABASE QUERY REPRESENTATION

METHODS AND SYSTEMS FOR AUGMENTATION AND FEATURE CACHE

TECHNIQUES FOR NEGATIVE ENTITY AWARE AUGMENTATION

TECHNIQUES FOR POSITIVE ENTITY AWARE AUGMENTATION USING TWO-STAGE AUGMENTATION

TECHNIQUES FOR TWO-STAGE ENTITY-AWARE DATA AUGMENTATION

TRAINING DATA GENERATION TO FACILITATE FINE-TUNING EMBEDDING MODELS

LEXICAL DROPOUT FOR NATURAL LANGUAGE PROCESSING

GAZETTEER INTEGRATION FOR NEURAL NAMED ENTITY RECOGNITION

Task-oriented dialog suitable for a standalone device

System and techniques for handling long text for pre-trained language models

PATH DROPOUT FOR NATURAL LANGUAGE PROCESSING

WIDE AND DEEP NETWORK FOR LANGUAGE DETECTION USING HASH EMBEDDINGS

PROHIBITING INCONSISTENT NAMED ENTITY RECOGNITION TAG SEQUENCES

FINE-TUNING MULTI-HEAD NETWORK FROM A SINGLE TRANSFORMER LAYER OF PRE-TRAINED LANGUAGE MODEL

FUSION OF WORD EMBEDDINGS AND WORD SCORES FOR TEXT CLASSIFICATION

Framework for focused training of language models and techniques for end-to-end hypertuning of the framework

Reduced training for dialog systems using a database

Reduced training intent recognition techniques

Techniques for dialog processing using contextual data

Stop word data augmentation for natural language processing

Compressing neural networks for natural language understanding

Streamlining dialog processing using integrated shared resources

Task-oriented dialog suitable for a standalone device