Systematic tuning of text analytic annotators

A system for tuning one or more text analytic annotators comprising:

• a computer system including at least one processor configured to:
• generate a data structure including domain information and one or more information extraction rules, wherein the domain information includes one or more enumerators for one or more data types of the domain, one or more text forms of the enumerators representing forms of the enumerators appearing in text, and one or more context patterns for the text forms, wherein the one or more extraction rules are associated with the enumerators, and wherein the domain information is generic with respect to requirements of more than one organization;
• execute an annotator construction and tuning module that tunes the one or more extraction rules to a specified set of documents with specialized information including domain specific terminology of a specific organization, the annotator construction and tuning module configured to:
• identify one or more additional context patterns and text forms within the set of documents for the enumerators of the data structure in a first iteration through the set of documents based on exact matches between tokens within the set of documents and the one or more text forms;
• identify one or more additional context patterns and text forms within the set of documents for the enumerators of the data structure in a second iteration through the set of documents based on partial matches between tokens within the set of documents and the one or more text forms;
• update the data structure with the additional context patterns and text forms from the first and second iterations;
• and
• analyze the set of documents based on the updated data structure and generate one or more additional extraction rules based on the analysis;
• configure one or more text analytic annotators for the specialized information based at least on the additional extraction rules;
• and
• process documents with the specialized information via the configured text analytic annotators.

A computer program product for tuning one or more text analytic annotators comprising:

• a computer readable storage medium having computer readable program code embodied therewith, the computer readable program code comprising computer readable program code that, when executed by at least one processor, configures the at least one processor to:
• generate a data structure including domain information and one or more information extraction rules, wherein the domain information includes one or more enumerators for one or more data types of the domain, one or more text forms of the enumerators representing forms of the enumerators appearing in text, and one or more context patterns for the text forms, wherein the one or more extraction rules are associated with the enumerators, and wherein the domain information is generic with respect to requirements of more than one organization;
• execute an annotator construction and tuning module that tunes the one or more extraction rules to a specified set of documents with specialized information including domain specific terminology of a specific organization, the annotator construction and tuning module configured to:
• identify one or more additional context patterns and text forms within the set of documents for the enumerators of the data structure in a first iteration through the set of documents based on exact matches between tokens within the set of documents and the one or more text forms;
• identify one or more additional context patterns and text forms within the set of documents for the enumerators of the data structure in a second iteration through the set of documents based on partial matches between tokens within the set of documents and the one or more text forms;
• update the data structure with the additional context patterns and text forms from the first and second iterations;
• and
• analyze the set of documents based on the updated data structure and generate one or more additional extraction rules based on the analysis;
• configure one or more text analytic annotators for the specialized information based at least on the additional extraction rules;
• and
• process documents with the specialized information via the configured text analytic annotators.