Discovering terms using statistical corpus analysis

A computer program product comprising a computer readable storage medium having stored thereon:

• program instructions to receive a predefined lexicon of domain term(s) relating to a domain, where the domain term(s) include nouns and/or noun phrases;
• program instructions to identify a set of initial context word(s) from a corpus, where each initial context word of the set of initial context word(s) appears, in the corpus, within a certain number of words of at least one domain term of the lexicon of domain term(s);
• program instructions to identify a first term from a corpus, where the first term is different from the domain term(s) of the lexicon of domain term(s), and where the first term is identified, based, at least in part, on the contextual use of the first term in the corpus matching the contextual use of at least one domain term of the lexicon of domain term(s) in the corpus, according to at least one context word of the first term in the corpus matching at least one initial context word of the set of initial context word(s);
• program instructions to add the first term to the lexicon of domain term(s), thereby creating a revised lexicon of domain term(s) and a set of first term context word(s), where each first term context word of the set of first term context word(s) appears, in the corpus, within a certain number of words of the first term;
• and
• program instructions to identify a second term from the corpus, where the second term is different from the domain term(s) of the revised lexicon of domain term(s), and where the second term is identified based, at least in part, on the contextual use of the second term in the corpus matching the contextual use of the first term in the corpus, according to at least one context word of the second term in the corpus matching at least one first term context word of the set of first term context word(s).

A computer system comprising:

• a processor(s) set;
• and
• a computer readable storage medium;
• wherein:
• the processor(s) set is structured, located, connected and/or programmed to run program instructions stored on the computer readable storage medium;
• and
• the stored program instructions include:
• program instructions to receive a predefined lexicon of domain term(s) relating to a domain, where the domain term(s) include nouns and/or noun phrases;
• program instructions to identify a set of initial context word(s) from a corpus, where each initial context word of the set of initial context word(s) appears, in the corpus, within a certain number of words of at least one domain term of the lexicon of domain term(s);
• program instructions to identify a first term from a corpus, where the first term is different from the domain term(s) of the lexicon of domain term(s), and where the first term is identified, based, at least in part, on the contextual use of the first term in the corpus matching the contextual use of at least one domain term of the lexicon of domain term(s) in the corpus, according to at least one context word of the first term in the corpus matching at least one initial context word of the set of initial context word(s);
• program instructions to add the first term to the lexicon of domain term(s), thereby creating a revised lexicon of domain term(s) and a set of first term context word(s), where each first term context word of the set of first term context word(s) appears, in the corpus, within a certain number of words of the first term;
• and
• program instructions to identify a second term from the corpus, where the second term is different from the domain term(s) of the revised lexicon of domain term(s), and where the second term is identified based, at least in part, on the contextual use of the second term in the corpus matching the contextual use of the first term in the corpus, according to at least one context word of the second term in the corpus matching at least one first term context word of the set of first term context word(s).