Oki Electric Industry Co., Ltd.

Mihoko Kitamura

Toshiki Murata

Sayori Shimohata

Atsushi Ikeno

Hideki Yamamoto

Tatsuya Sukehiro

Masachika Fuchigami

Ikuo Orihara

Shigehiro Kato

Miho Tanaka

Miki Sasaki

Tsuyoshi Fukui

A dialogue control system that uses an ontology that systematically expresses domain knowledge representing concepts and relationships between concepts to determine questions for a user and implements the questions, and implements a dialogue in accordance with received user answers. One or more dimension-classified ontologies and a basic ontology are stored, a concept from a user response is specified as a condition, and one or a plural number of the dimension-classified ontologies that meet the specified condition are fetched. The content of the fetched dimension-classified ontology/ies is overwritten on the basic ontology, in order according to dimension priorities from the dimension-classified ontology with the lowest dimension priority, and a multidimensional ontology is generated. The dialogue control system uses this multidimensional ontology to control the dialogue.

Dialogue control system, method and computer readable storage medium, and multidimensional ontology processing system, method and computer readable storage medium

The present invention provides an apparatus and method for natural language processing capable of providing an appropriate result of natural language processing. More specifically, the present invention provides a natural language processing apparatus for achieving a syntax analysis and/or a syntax generation by using natural language patterns with, at least, pattern name and pattern component. The natural language processing apparatus comprises dictionary reference means for picking up one or more natural language patterns applicable for the syntax analysis and/or the syntax generation among the natural language patterns prepared in a pattern dictionary in advance, pattern inspection means for inspecting whether the applicable natural language patterns meet a tree structure or not, and pattern application means for applying the natural language patterns to the tree structure if the natural language patterns meet the tree structure.

Apparatus and method for natural language processing

Given a source text, a desired translation of the source text into a target language, and a machine-readable dictionary, a first set of morphemes in the target language is generated from the source text, typically by using the dictionary to perform a machine translation of the source text. The second text is analyzed into a second set of morphemes in the target language. Differences between the first and second sets of morphemes are found, and morphemes corresponding to the differences are taken from the source text. Existing information including these source-text morphemes is extracted from the dictionary, and new information to be added to the dictionary is automatically generated from the extracted information and the differences. This process generates comparatively short dictionary entries, corresponding only to the differences between the two set of morphemes, and therefore creates useful dictionary entries while saving dictionary space.

Apparatus and method for adding information to a machine translation dictionary

There is provided a morphological analysis method and device whereby, even if unknown words are present, processing can be effected with high accuracy and at high speed and economy of resources can be achieved. Expanded characters e.sub.i are generated by adding to each character c.sub.i of input text, in addition to word division information d.sub.i, expansion information including required arbitrarily selectable information such as tag information, and all possible expanded character sequences are generated. Beforehand, by training, the partial chain probabilities (appearance probabilities) of N-gram (where, normally N=1 or 2 or 3) character sequences are stored in an expanded character table. The partial character sequences of the expanded character sequences are successively extracted from the beginning of the expanded character sequence and the respective partial chain probabilities are found by referring to the expanded character table, and the product of the thus-found partial chain probabilities is obtained. This product is found for all the expanded character sequences, and analysis results etc. consisting of a row of word sequences in order of character sequences corresponding to largest such products, as well as a row of tag sequences and/or arbitrarily selectable information is output as the morphological analysis result.

Morphological analysis method and device and Japanese language

Growing community of inventors

Kyoto, Japan

Mihoko Kitamura