System, method, program product, and networking use for recognizing words and their parts of speech in one or more natural languages

Abstract

The present invention is disclosed for recognizing one or more words not listed in a dictionary data base. If there is no valid word obtained, a statistical process checks one or more sequences of a sub set of two or more characters in the word to determine a probability that the word is a valid word. In alternative embodiments, the invention includes a prefix removal process, a suffix removal process, a root process, and/or a combination process. The prefix removal process removes one or more prefixes from a word where the prefixes are preferably in a prefix list. The prefix removal preferably is constrained by one or more prefix removal rules. The prefix removal process also obtains prefix information about the removed prefix (e.g., from a dictionary data base or prefix list). The suffix removal process removes one or more suffixes from the word where the suffixes are preferably in a suffix list. Preferably, the suffix removal is constrained by one or more suffix removal rules. The suffix removal process also obtains suffix information about the removed suffix (e.g., from the dictionary data base or suffix list). The root process obtains root information about a root word from the dictionary database. (The root word is the word with the prefix and suffix removed.) The combination process then determines if the prefix, the root, and the suffix can be combined into a valid word as defined by one or more combination rules. The combination process then obtains one or more of the possible parts of speech of the valid word, if there is a valid word, and stores the parts of speech with the valid word in the dictionary database (or other memory location).

Dependencies are inferred from the claim text.