Abstract: An information processing device according to the present application includes an extraction unit and a subsequent stage generation unit. The extraction unit extracts a last conversation of a feedback utterance estimated to indicate a predetermined reaction of a second utterance subject relative to an utterance made by a first utterance subject, from a set of a plurality of conversations, based on a score assigned to the feedback utterance. The subsequent stage generation unit generates a subsequent stage classifier for deriving an index indicating a category of an unknown conversation, based on the last conversation extracted by the extraction unit.

Abstract: An advertisement distribution device according to the present application includes a distribution unit. The distribution unit distributes advertising content while switching an advertisement distribution process in accordance with a predetermined target figure within the range an advertisement listing fee paid to a provider of a Web page on which the advertising content is placed reaches the predetermined target figure.

Abstract: An information processing device according to the present application includes an extraction unit and a subsequent stage generation unit. The extraction unit extracts a last conversation of a feedback utterance estimated to indicate a predetermined reaction of a second utterance subject relative to an utterance made by a first utterance subject, from a set of a plurality of conversations, based on a score assigned to the feedback utterance. The subsequent stage generation unit generates a subsequent stage classifier for deriving an index indicating a category of an unknown conversation, based on the last conversation extracted by the extraction unit.

Abstract: A generating device includes an accepting unit that accepts a speech of a user. The generating device includes a generating unit that, by inputting the speech of the user to a single model in which a group of parameters are learned simultaneously to output a response directly from a speech, generates a response to the speech.

Abstract: An advertisement distribution device according to the present application includes a distribution unit. The distribution unit distributes advertising content while switching an advertisement distribution process in accordance with a predetermined target figure within the range an advertisement listing fee paid to a provider of a Web page on which the advertising content is placed reaches the predetermined target figure.

Abstract: Herein disclosed is a data classifying device whereby support vector machine performs a data classification based on a learning result obtained by performing an active learning method, comprises: a correct answer database adapted to store therein examples and their correct answer classes; a pooling section adapted to pool examples to which correct answer classes are not yet assigned; an SVM learning section adapted to perform learning of the support vector machine by using correct answer examples stored in the correct answer database; an SVM classifying section adapted to store therein the learning result obtained by the SVM learning section and perform the data classification based on the learning result thus stored therein; an active learning-purposed example selecting section adapted to select examples for use in the active learning from the pooling section by using the learning result; and a pooled example increasing section adapted to acquire new examples to which correct answer classes are not yet assig

Abstract: An information retrieval processing system includes a search question input unit to receive a search question of a user. A context acquisition unit then acquires a context from a context action correspondence table that corresponds to the received search question. An action which corresponds to the acquired context is then used to select an information retrieval system from a plurality of information retrieval systems. A history recording unit records a history of the questions received by the search question input interface unit such that the recorded history is used to select the information retrieval system. Accordingly, the retrieval system automatically reads the context into which the user will attempt to input the information and automatically select an information retrieval system from among the plurality of information retrieval systems.

Abstract: The present invention is intended to allow a user to easily and precisely extract related terms through use of mutual information without requiring morphological analysis or syntax analysis, by constituting a related term extraction apparatus from preceding-and-subsequent term extraction means for extracting a preceding term occurring prior to a specified term or a subsequent term occurring subsequent to the same in text data; a frequency calculation means for calculating the occurrence frequencies of the specified term, the preceding terms, and the subsequent terms; probability-of-occurrence calculation means for calculating the occurrence probabilities of the preceding and subsequent terms together with the occurrence probability of the specified term; probability-of-concurrence calculation means for calculating the probabilities of the preceding and subsequent terms cooccurring with the specified term; order-dependent degree-of-association calculation means for calculating an order-dependent degrees of the

Abstract: A registration apparatus for a compound-word dictionary automatically and suitably determines whether a combination of character strings must be registered as one entry word in a compound-word dictionary. The registration apparatus comprises a character string segmenter which segments a compound-word into its individual words. The frequency that each individual word occurs in entry words of a compound-word dictionary is determined by an occurrence frequency calculator. An evaluation value calculator calculates an evaluation value based on the occurrence frequencies. Based on this evaluation value, a register determiner then determines if the compound-word is to be registered in the compound-word dictionary. The process for obtaining an evaluation value may depend on the number of component words and contents of the existing dictionary, a physical size limit on the compound-word dictionary and the purpose of use of the dictionary.

Abstract: A pattern matching rule for recognizing a weakly linked idiom is previously held in a pattern matching section. If a weakly linked idiom which is registered in the pattern matching rule and has separately placed portions is present in an input sentence, the pattern matching section recognizes the idiom. If the weakly linked idiom is recognized by the pattern matching section, the idiom is replaced by a series of symbolized pattern expressions in a replacing section. A sentence subjected to the replacement process in the replacing section is given to an analyzing section. The analyzing section treats the series of symbolized pattern expressions as one idiom and analyzes the sentence. As a result, the result of analysis in which the weakly linked idiom is adequately processed is obtained as an output of the analyzing section.