Abstract: A Chinese word segmentation apparatus relates to processing of a Chinese sentence input to a computer. A character-to-phonetic converter of the segmentation apparatus initially converts a Chinese sentence into a phonetic symbol string while referring to a character phonetic dictionary and a ductionary for characters with different pronunciations. Thereafter, a candidate word-selector refers to a system dictionary to retrieve all of the possible candidate characters or words in the phonetic symbol string and relevant information, such as frequency of use, using the phonetic symbols as indexing terms. Unfeasible candidate characters or words are discarded. Subsequently, an optimum candidate character string-decider builds a candidate word network using starting and ending positions of each candidate character or word in the input sentence as indexing terms.

Abstract: An on-line handwritten Chinese character recognition apparatus based on character shapes uses a reference file for look-up of compressed codes-sequence codes in a conventional input method founded on dismantling by character shapes as reference when comparing character to reduce the number of matching templates required in the on-line handwritten Chinese character recognition system and to lower the time for matching. Input handwritten Chinese characters are dismantled into constituting radicals. Thereafter, with reference to code retrieving rules of the input method, and based on the character composing method of handwritten characters, radicals for comparison are retrieved. Then, the compression formula of the input method is used to compress the codes of the base radicals, and the compressed codes are compared with contents of the input method reference file to obtain the sequence codes of candidate characters.

Abstract: The Chinese generation apparatus for machine translation utilizes statistic data for Chinese generation instead of a large number of semantic, grammatical related rules, the statistic data being retrieved from a tagged Chinese corpus. In order to overcome the problem that a large number of semantic or grammatical rules are needed in Chinese generation, the constitution of a Chinese sentence is divided into basic sentence pattern item and other items. The probability of the possibly generated basic sentence pattern of each Chinese verb and the location probability of the other item in the basic sentence pattern are initially retrieved from the Chinese corpus and are stored in the buffer unit. The best basic sentence pattern and the location of the other items can be found in accordance with each constitution item of the intermediate form of Chinese and the statistic information in the buffer unit with the use of branch-and-bound method, so that the most suitable Chinese sentence can be generated.

Abstract: A machine translation apparatus includes: a transfer dictionary for translation word searching for storing therein a semantic code representative of semantic categorization of a source language word, a dominated code which is a semantic code of a word relatable to the source language word, and a translation word of a target language corresponding to the dominated code; a dominated code and semantic code searching unit for executing a logical AND operation applicable to a word at each node of an intermediate structure obtained by parsing an inputted source language sentence, to be performed on the dominated code of the each node and the semantic code of a node related to the each node, which are respectively stored in the transfer dictionary for translation word searching, and determining proper ones of the dominated code and the semantic code, respectively and a translation word searching unit for searching a translation word for each node corresponding to the dominated code obtained by the dominated code and