Systems and methods for natural language processing

摘要

Methods, systems and computer programs for automatic, highly accurate machine comprehension of a plurality of segments of free form unstructured text in a natural language. The system answers a plurality of complex, free-form questions asked in a natural language, based on the totality of input text. The system further uses a multi-dimensional data model to measure the total effects of actions/verbs acting on various unique nouns present in the input text. The system may convert the questions into another multi-dimensional data model and may then compare the two data models in program memory to derive the answers to the posed questions. The system may then automatically detect unknown words and optionally look them up in digital information sources, such as online dictionaries and encyclopedias, to fill in the gaps in knowledge to answer the questions with expert-like reliability.

主权项

1. A method for natural language processing, comprising the steps of:
providing a parallel computer processing system performing the natural language processing, wherein the system is configured to simultaneously perform the natural language processing on multiple sources of text, wherein the system comprises a plurality of computer systems, wherein each computer system comprises: a computer processor unit; and a non-transitory computer readable medium operably associated with the computer processor unit, the non-transitory computer readable medium storing instructions executable by the computer processor unit to perform the steps of: receiving input text, the input text comprising a first plurality of words; applying a predetermined scale to the received input text to obtain a semantic relationship scale-web of the received input text; disambiguating the received input text into a second plurality of words; linking the second plurality of words based on the disambiguation; applying a predefined common sense rule to the predetermined scale to modify the semantic relationship scale-web; and providing an answer to a question regarding the received multiple sources of input text based on the modified semantic relationship scale-web linking, or the application of the predefined common sense rule.