Method and system for extracting keywords from text

A non-transitory computer readable medium, storing instructions for executing a process, the instructions comprising:

• extracting, by a processor, keywords and dependency information from a text;
• and
• generating, by the processor, a co-occurrence dictionary for the text, the generating the co-occurrence dictionary comprising:
• selecting, by the processor, ones of the keywords for inclusion in the co-occurrence dictionary based on a number of times the ones of the keywords satisfy the dependency rules and user defined confidence levels;
• determining, by the processor, for the selected ones of the keywords included in the co-occurrence dictionary, surrounding words to be associated with the selected ones of the keywords in the co-occurrence dictionary based on a number of instances of co-occurrence of the surrounding words with the selected ones of the keywords;
• generating, by the processor, weights for each of the selected ones of the keywords in the co-occurrence dictionary based on a number of the surrounding words associated with the selected ones of the keywords;
• and
• generating, by the processor, confidence scores for each of the selected ones of the keywords based on the weights and correlation between each of the selected ones of the keywords,
• wherein application of the user defined confidence levels in the keyword selection reduces processing power required in the generation of confidence scores by removing keywords for consideration, and
• wherein the dependency rules comprise identifying extracted keywords that are a noun preceded by a noun, an adjective preceded by an adjective, or an adverb preceded by a verb as the ones of keywords to be selected for inclusion, wherein the selecting ones of the keywords for inclusion in the co-occurrence dictionary based on the number of times the ones of the keywords satisfy the dependency rules comprises:
• incrementing a first counter for when the dependency rules are satisfied;
• incrementing a second counter for when the dependency rules are not satisfied;
• and
• selecting the ones of the keywords for inclusion for when the first counter exceeds the second counter.

An apparatus, comprising:

• a processor, configured to:
• extract keywords and dependency information from a text;
• and
• generate a co-occurrence dictionary for the text by:
• selecting ones of the keywords for inclusion in the co-occurrence dictionary based on a number of times the ones of the keywords satisfy the dependency rules and user defined confidence levels;
• determining for the selected ones of the keywords included in the co-occurrence dictionary, surrounding words to be associated with the selected ones of the keywords in the co-occurrence dictionary based on a number of instances of co-occurrence of the surrounding words with the selected ones of the keywords;
• generating weights for each of the selected ones of the keywords in the co-occurrence dictionary based on a number of the surrounding words associated with the selected ones of the keywords;
• and
• generating, by the processor, confidence scores for each of the selected ones of the keywords based on the weights and correlation between each of the selected ones of the keywords,
• wherein application of the user defined confidence levels in the keyword selection reduces processing power required in the generation of confidence scores by removing keywords for consideration, and
• wherein the dependency rules comprise identifying extracted keywords that are a noun preceded by a noun, an adjective preceded by an adjective, or an adverb preceded by a verb as the ones of keywords to be selected for inclusion;
• wherein the processor is configured to select ones of the keywords for inclusion in the co-occurrence dictionary based on the number of times the ones of the keywords satisfy the dependency rules by:
• incrementing a first counter for when the dependency rules are satisfied;
• incrementing a second counter for when the dependency rules are not satisfied;
• and
• selecting the ones of the keywords for inclusion for when the first counter exceeds the second counter.