Systems and methods for determining lexical associations among words in a corpus

A computer-implemented system for automatically identifying one or more target words of a corpus that have a lexical relationship to a plurality of provided cue words, the system comprising:

• a processing system;
• and
• computer-readable memory in communication with the processing system encoded with instructions for commanding the processing system to execute steps comprising:
• receiving a plurality of cue words at the system, the processing system executing a software application that is configured to accept the plurality of cue words based on an input received from a user, the plurality of cue words being received from one or more data input devices configured to be used by the user to input the plurality of cue words;
• processing each cue word of the plurality of cue words to determine one or more inflectional variants of the cue word;
• searching the cue words and the inflectional variants across entries of a dataset or database to determine candidate words that have a lexical association with the cue words, the dataset or database comprising statistical lexical information derived from a corpus of documents, the statistical lexical information including (i) first numerical values indicative of probabilities of word pairs appearing together as adjacent words in a well-formed text, and (ii) second numerical values indicative of probabilities of word pairs appearing together within a paragraph of a well-formed text;
• for each candidate word,
• determining a statistical association score between the candidate word and each of the cue words using the first and second numerical values included in the statistical information, and
• generating an aggregate score for each of the candidate words based on the statistical association scores;
• selecting one or more of the candidate words to be the one or more target words based on the aggregate scores of the candidate words;
• and
• outputting via a display the selected one or more candidate words in a graphic or alphanumeric format, the system being coupled to the display via a display interface.

A non-transitory computer-readable storage medium for automatically identifying one or more target words of a corpus that have a lexical relationship to a plurality of provided cue words, the computer-readable storage medium comprising computer executable instructions which, when executed, cause a processing system to execute steps comprising:

• receiving a plurality of cue words, the processing system executing a software application that is configured to accept the plurality of cue words based on an input received from a user, the plurality of cue words received from one or more data input devices configured to be used by the user to input the plurality of cue words;
• processing each cue word of the plurality of cue words to determine one or more inflectional variants of the cue word;
• searching the cue words and the inflectional variants across entries of a dataset or database to determine candidate words that have a lexical association with the cue words, the dataset or database comprising statistical lexical information derived from a corpus of documents, the statistical lexical information including (i) first numerical values indicative of probabilities of word pairs appearing together as adjacent words in a well-formed text, and (ii) second numerical values indicative of probabilities of word pairs appearing together within a paragraph of a well-formed text;
• for each candidate word,
• determining a statistical association score between the candidate word and each of the cue words using the first and second numerical values included in the statistical information, and
• generating an aggregate score for each of the candidate words based on the statistical association scores;
• selecting one or more of the candidate words to be the one or more target words based on the aggregate scores of the candidate words;
• and
• outputting via a display the selected one or more candidate words in a graphic or alphanumeric format.

A computer-implemented method of identifying one or more target n-grams of a corpus that have a lexical relationship to a plurality of provided cue words, the method comprising:

• receiving a plurality of cue words at a computer system, the computer system executing a software application that is configured to accept the plurality of cue words based on an input received from a user, the plurality of cue words being received from one or more data input devices configured to be used by the user to input the plurality of cue words;
• processing each cue word with a processing system of the computer system to determine one or more inflectional variants of the cue word;
• searching the cue words and the inflectional variants across entries of a dataset or database with the processing system to determine candidate n-grams that have a lexical association with the cue words, the dataset or database comprising statistical lexical information derived from a corpus of documents, the statistical lexical information including (i) first numerical values indicative of probabilities of word pairs appearing together as adjacent words in a well-formed text, and (ii) second numerical values indicative of probabilities of word pairs appearing together within a paragraph of a well-formed text;
• for each candidate n-gram,
• determining, using the processing system, a statistical association score between the candidate n-gram and each of the cue words using the first and second numerical values of the dataset, and
• generating, using the processing system, an aggregate score for each of the candidate n-grams based on the statistical association scores;
• selecting one or more of the candidate n-grams to be the one or more target n-grams based on the aggregate scores of the candidate n-grams;
• and
• outputting via a display the selected one or more candidate n-grams in a graphic or alphanumeric format, the computer system being coupled to the display via a display interface.