Natural Language Processing for Descriptive Language Analysis
AssigneeThe United States of America as represented by the Secretary of the Navy
InventorAlicia L Scott
Life of this patent
Estimating the term…
Abstract
The present invention relates to a system that uses natural language processing (NLP) to read data from a file and analyze the data based on user defined parameters. According to an illustrative embodiment of the present disclosure, a system can process and analyze a data file by finding trending themes across data entries. According to a further illustrative embodiment of the present disclosure, the system can search for reoccurring words/phrases based on Ngrams (i.e. n-grams). The system can be adapted to search for Ngrams of varying length depending on the information sought and can sort the results by Ngram length.
Claims3
A method of processing text comprising:
- identifying at least one data file comprising narrative information, wherein the narrative information comprising a plurality of data entries;
- extracting the narrative information from the data files;
- applying a plurality of natural language processing (NLP) algorithms to the narrative information to generate NLP results, wherein the NLP algorithms comprise finding word level n-grams for a plurality of word level n-gram lengths and counting repeating n-gram instances within each data entry;
- counting a number of repeating n-gram instances across the plurality of data entries;
- sorting the NLP results for each n-gram based on the number of repeating n-gram instances across the plurality of data entries;
- and
- creating an output data file comprising the NLP results.
A natural language processing (NLP) system comprising:
- a non-transitory computer readable storage medium operable for storing a plurality of machine readable computer instructions operable to control one or more elements of a NLP processing system comprising:
- a first section of machine readable computer instructions adapted to initiate the system;
- a second section of machine readable computer instructions adapted to load data files into the system and extract narrative information from the data files;
- a third section of machine readable computer instructions adapted to execute a plurality of NLP algorithms on the narrative information to generate NLP results;
- a fourth section of machine readable computer instructions adapted to clarify and filter the NLP results;
- a fifth section of machine readable computer instructions adapted to output the NLP results to an output file.
A method of processing text comprising:
- providing a non-transitory computer readable storage medium operable for storing a plurality of machine readable computer instructions operable to control one or more elements of a NLP processing system comprising:
- a first section of machine readable computer instructions adapted to initiate the system;
- a second section of machine readable computer instructions adapted to load data files into the system and extract narrative information from the data files;
- a third section of machine readable computer instructions adapted to execute a plurality of NLP algorithms on the narrative information to generate NLP results;
- a fourth section of machine readable computer instructions adapted to clarify and filter the NLP results;
- a fifth section of machine readable computer instructions adapted to output the NLP results to an output file;
- identifying at least one data file comprising narrative information, wherein the narrative information comprising a plurality of data entries;
- extracting the narrative information from the data files;
- applying a plurality of natural language processing (NLP) algorithms to the narrative information to generate NLP results, wherein the NLP algorithms comprise finding word level n-grams for a plurality of word level n-gram lengths and counting repeating n-gram instances within each data entry;
- counting a number of repeating n-gram instances across the plurality of data entries;
- sorting the NLP results for each n-gram based on the number of repeating n-gram instances across the plurality of data entries;
- and
- creating an output data file comprising the NLP results.
Dependencies are inferred from the claim text.