Abstract: 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.

Abstract: 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.

Abstract: A user speech analyzing component poses, to a user, question sentences for respective ones of a plurality of attributes, and analyzes an attribute value for each of the attributes from an answer sentence from the user to the sentence question. A user data holding component, as a result of analysis, holds user data that allows the plurality of attributes, and respective user attribute values for the attributes to correspond to one another. A matching component, when an acquisition ratio of the attribute values from the user with respect to all of the attributes is a predetermined value or greater, selects at least one target data candidate that matches each of the attributes and each of the attribute values of the user data, from a plurality of target data. A dialogue control component outputs each of the target data candidates selected, to the user's side.

Abstract: A translation evaluation apparatus is includes: a parallel translation corpus data base (310) that stores, in an associated manner, base original texts and respective model translated texts of the base original texts, a parallel translation linking unit (225) that links the model translated texts to create a linked model translated text, and links the base original texts that are associated with the model translated texts that form the linked model translated text to create a linked original text; an evaluation target translated text input unit (110) that is used to input evaluation target translated text and that corresponds with the base original text; and an evaluation value computation unit (235) that links the evaluation target translated text to create a linked evaluation target translated text, and compares the linked evaluation target translated text and the linked model translated text to evaluate the translation quality of the evaluation target translated text.

Abstract: 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.

Abstract: 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.

Abstract: The relationship between documents is detected in consideration of the texts of the documents. A document relationship inspection apparatus which inspects the relationship between constituent elements of a first document and constituent elements of a second document, includes a logical structure parsing section which parses a logical structure of a sentence block including at least one sentence in the constituent elements of the first document and which parses a logical structure of a sentence block including at least one sentence in the constituent elements of the second document, and a relationship detection section which detects the relationship between the sentence block of the first document and the sentence block of the second document on the basis of a parsing result from the logical structure parsing section.

Abstract: There are provided a natural language processing apparatus, a natural language processing method, and a natural language processing program which can improve the accuracy of a parsing result in syntax parsing using a pattern rule. In the natural language processing apparatus, the natural language processing method, and the natural language processing program, a pattern rule with sentence ID to which a sentence ID representing the possibility of simultaneously applying the sentence ID to the same sentence is prepared in advance. When syntax parsing of an input sentence is performed with reference to the prepared pattern rule, a large number of pattern rules to which the same sentence ID is given are included in the parsing result.

Abstract: In a bilingual dependency structural alignment system and method of the invention, in order to align the dependency structure of the first language sentences and the second language sentences of the bilingual text without complicating the processing but with good accuracy and to make the coverage of alignment higher, alignment is performed on the dependency structures of the first language sentence and the second language sentence in the bilingual document by a bilingual dictionary with degree of parallelism with a word or word string as a header, and, at the time thereof, if there is at least a part that can not be aligned and/or if there are plural candidates of correspondences in at least a part, the lacking alignment of the dependency structures is obtained or optimum correspondence of the plural candidates is determined, while satisfying the condition that the dependency structures are held in the first language sentence and the second language sentence, respectively, and on the condition that the evalua

Abstract: 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.

Abstract: 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.

Abstract: 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.