METHOD OF GENERATING WORD DIVISION MODEL
    1.
    发明专利

    公开(公告)号:JP2003263427A

    公开(公告)日:2003-09-19

    申请号:JP2002062625

    申请日:2002-03-07

    Abstract: PROBLEM TO BE SOLVED: To provide a method of dividing a sentence by learning without a teacher, without using heuristics. SOLUTION: This method of generating a word division model using a training sentence without word division comprises a first step of generating a network of dividable candidate words from all the given training sentences using a given dictionary entry, a second step of generating such a model as to minimize entropy, to the network of the candidate words generated in the first step, and a third step of smoothing the transition probability value which is the probability value for predicting the following word from a known word or a known word pair. COPYRIGHT: (C)2003,JPO

    LANGUAGE MODEL ADAPTATION METHOD
    2.
    发明专利

    公开(公告)号:JP2003248496A

    公开(公告)日:2003-09-05

    申请号:JP2002047047

    申请日:2002-02-22

    Abstract: PROBLEM TO BE SOLVED: To provide a language model adaptation method capable of creating a language model adaptable to a new task by using a mono-lingual corpus in the new task described in a language other than the language of the language model to be made adaptive. SOLUTION: The language model adaptation method for creating the language model of a first language adaptable to the new task when the task of a voice translation device is extended, is provided with a first step to create a second mono-lingual corpus in the new task described in the first language by translating the first mono-lingual corpus of the new task described in a second language other than the first language into the first language using a machine translation device, and a second step to make the language model adaptive based on the second mono-lingual corpus in the new task created in the first step. COPYRIGHT: (C)2003,JPO

Patent Agency Ranking