Systems and methods for facilitating text analysis

Inventors

Butler, JoAnna Jean • Cooper, Casey Hatcher • Flint, Jaden Kadesh • Rogers, Jason LeVoy • Zook, Keith Boyd • RUSSELL, Kyle Jordan

Assignees

Intuitive Research and Technology Corp

Abstract

A system for facilitating text analysis is configurable to (i) receive input text data comprising a set of reference text and at least a first set of text, wherein the set of reference text and the first set of text each comprise structured components; process the input text data utilizing a syntax and verb usage module of a natural language processing (NLP) layer; generate a mapping of structured components of the first set of text to structured components of the set of reference text by processing output of the syntax and verb usage module utilizing a similarity analysis module or a categorization module of the NLP layer; and generate an output depicting one or more aspects of the mapping.

Core Innovation

The invention facilitates text analysis by processing input text data utilizing a syntax and verb usage module of an NLP layer. The input text data comprises a set of reference text and at least a first set of text, and the set of reference text and the first set of text each comprise structured components. Output of the syntax and verb usage module enables downstream mapping of structured components between the first set of text and the set of reference text.

The invention uses output of the syntax and verb usage module as input to a categorization module of the NLP layer and as input to a similarity analysis module of the NLP layer. The categorization module maps structured components of the first set of text to structured components of the set of reference text by generating embeddings based on the output of the syntax and verb usage module and categorizing the output relative to predefined groupings determined based on the set of reference text.

The similarity analysis module maps structured components by comparing, in an embedding space, embeddings generated based on the output of the syntax and verb usage module and embeddings generated based on the set of reference text. The invention fuses output of the categorization module and the similarity analysis module to generate a mapping of structured components of the first set of text to structured components of the set of reference text. It generates and presents, on a user interface, an output depicting one or more aspects of the mapping and a prompt associated with an indication of one or more structured components that are mapped, receives user input directed to the prompt indicating rejection of the mapping, and tunes one or more modules of the NLP layer based on the user input.

Claims Coverage

Independent claims are directed to a system and a method implementing an NLP pipeline with a syntax and verb usage module and dual mapping via categorization and similarity analysis, followed by fusion, user-interface presentation with a prompt, user rejection feedback, and tuning of NLP modules. Across the independent claims, the core coverage includes both categorization relative to predefined groupings and similarity mapping via embedding-space comparisons, with fused mapping outputs and interactive user feedback.

The independent claims cover an NLP-layer text analysis system and method that process reference and additional text sets with structured components using a syntax and verb usage module, then derive mappings by fusing two mapping pathways: categorization relative to predefined groupings and similarity analysis via embedding-space comparisons. The mapping is presented on a user interface with an associated prompt, user rejection feedback is received, and one or more modules of the NLP layer are tuned based on that feedback.

Stated Advantages

Documented Applications