Abstract: An improved method for correcting spelling errors in text wherein candidate expressions for replacing a misspelled word are assigned probability functions. The misspelled word can be replaced automatically with the candidate expression having the highest probability function or candidate expressions can be displayed to a user in rank order of their probability functions for the user to make a choice. The probability function for a candidate expression is based on (1) the probability of occurrence of the candidate expression appearing in text and/or (2) the probability of occurrence of the particular typographical modification needed to convert the candidate expression into the misspelled word.

Abstract: Apparatus and methods for determining whether a word/sense pair is proper for a context. Wide contexts (100 words) are employed for both training and testing, and testing is done by adding the weights of vocabulary words from the context. The weights are determined by Bayesian techniques which interpolate between the probability of occurrence of a vocabulary word in a conditional sample of the training text and the probability of its occurrence in the entire training text. A further improvement in testing takes advantage of the fact that a word is generally used in only a single sense in a single discourse. Also disclosed are automated training techniques including training on bilingual bodies of text and training using categories from Roget's Thesaurus.

Abstract: A method and apparatus for natural language processing using morphology and rhyming. The method and apparatus employ a hybrid of dictionary and rule-based approaches for both speech and speech recognition. In an illustrative embodiment of the present invention the pronunciation of a word is determined by rhyming the word, or components of the word, with a reference word, or components of the reference word. In another illustrative embodiment of the present invention, the spelling of a word is determined by rhyming the word, or components of the word, with a reference word, or components of the reference word.

Abstract: Methods for determination of parts of speech of words in a text or other non-verbal record are extended to include so-called Viterbi optimization based on stored statistical data relating to actual usage and to include noun-phrase parsing. The part-of-speech tagging method optimizes the product of individual word lexical probabilities and normalized three-word contextual probabilities. Normalization involves dividing by the contained two-word contextual probabilities. The method for noun phrase parsing involves optimizing the choices of, typically non-recursive, noun phrases by considering all possible beginnings and endings thereof, preferably based on the output of the part-of-speech tagging method.

Abstract: In text-to-speech generating arrangements, text is analyzed to determine the language source of words therein by successively selecting letter sequences of each word in the text. At least one signal representative of the probability that the text word corresponds to a particular language source is generated responsive to the selected letter sequences and a language source is selected for converting the text work to a phonetic string responsive to the probability representative signals.