Systems and methods for improved cybersecurity named-entity-recognition considering semantic similarity
AssigneesArizona Board of Regents on behalf of Arizona State University, Cyber Reconnaissance, Inc.
InventorsKazuaki Kashihara, Jana Shakarian
Life of this patent
Estimating the term…
Abstract
A computer-implemented system implements a named entity recognition (NER) model trained for automatic dataset labeling and corpus generation for cybersecurity entities. The NER model includes a semantic similarity measure to determine which category an unclassified/unlabeled word such as an ambiguous keyword with more than one meaning should belong to based on the semantic similarity of an entire sentence.
Claims6
A method for improved cybersecurity named entity recognition, comprising:
- categorizing, by a processor undiscovered keywords related to cybersecurity, including:
- accessing an ambiguous keyword of a given sentence, the ambiguous keyword having multiple meanings and b elonging to one or more of a plurality of categories,
- calculating a plurality of semantic similarity scores by calculating a similarity score for each of the plurality of categories based on semantic similarity of the category and context of the ambiguous keyword within the given sentence, and
- assigning the ambiguous keyword to a specific category of the plurality of categories associated with a maximum score of the plurality of semantic similarity scores.
A tangible, non-transitory, computer-readable media having instructions encoded thereon, such that a processor, executing the instructions, is configured to:
- access an ambiguous keyword of a given sentence, the ambiguous keyword having multiple meanings and belonging to one or more of a plurality of categories,
- calculate a plurality of semantic similarity scores by calculating a semantic similarity score for each of the plurality of categories based on semantic similarity of the category and context of the ambiguous keyword within the given sentence, and
- assign the ambiguous keyword to a specific category of the plurality of categories associated with a maximum score of the plurality of semantic similarity scores.
Dependencies are inferred from the claim text.