Nec Corporation

Nec Solution Innovators, Ltd.

Yuzuru Okajima

Kunihiko Sadamasa

Shinichi Ando

Satoshi Nakazawa

Kouichi Maruyama

Kosuke Yamamoto

Yoshio Ishizawa

Shohei Higashiyama

An information processing apparatus () acquires input data () and generates, by use of a neural network (), condition data () that indicate one or more conditions satisfied by the input data (). The information processing apparatus () determines prediction data () by use of a value determined based on correct answer data () associated with example data () that satisfy at least a part of conditions indicated by the condition data ().

Machine learning predictions by generating condition data and determining correct answers

An information processing apparatus () includes: a formal language query accepting unit () that accepts a query expression and correct answer data; a semi-structured data accepting unit () that accepts semi-structured data that includes text nodes; a node text extraction unit () that extracts natural language text from the text node, as node text; a node text expression generation unit () that receives the node text from the a converter () and obtains node text expressions; an answer calculation unit () that calculates an answer to the query expression with use of the node text expressions; and an update unit () that, if the answer calculated by the answer calculation unit () matches the correct answer data, updates parameters in the converter () such that the corresponding node text expression is more likely to be output in the converter ().

Information processing apparatus, information processing method, and computer readable recording medium

An information processing apparatusincludes an acceptance unita formal language generation unitan inference unitand an update unitThe formal language generation unitgenerates training expressions in a formal language based on parameters prepared in advance and pieces of text accepted by the acceptance unitThe inference unitexecutes at least one inference out of deductive inference and abduction on the above training expressions using a knowledge base prepared in advance. The update unitcompares an inference result of the inference unitwith a model answer input in advance, and updates parameters such that an inference result that matches the model answer is likely to be obtained through inference performed by the inference unit

Information processing apparatus, information processing method, and computer-readable recording medium

An information processing device according to the present invention includes: a memory; and a processor coupled to the memory. The processor performs operations. The operations includes: generating, based on language data, a predicate argument structure including a predicate and an argument being an object of the predicate; generating first data indicating co-occurrence of the predicate and the argument in the predicate argument structure; decomposing the first data into a plurality of pieces of second data including fewer elements than elements included in the first data, and generating, based on the second data, third data including potential co-occurrence of the predicate and the argument; selecting the predicate argument structure by using the first data and the third data, and calculating, by using the third data, a score for a pair of the predicate argument structures including the selected predicate argument structure; and selecting the pair, based on the score.

Information processing device, information processing method, and recording medium

This invention provides an information processing apparatus for learning parameters to convert a question in a natural language into a query expression in a formal language, including an acceptor accepting an input of a set of a question in the natural language and a correct answer to the question, a condition generator generating condition(s) to be satisfied by the formal language input on searching a database for the correct answer, a query expression generator generating a query expression in the formal language corresponding to the question using parameters of the converter to satisfy any of the at least one condition, an answer acquirer acquiring an answer to the question based on a search of the database using the generated query expression, and a updater updating the parameters such that the question is converted with priority into the generated query expression when the answer and the correct answer match.

Information processing system, information processing apparatus, information processing method, and information processing program

An information processing device () processes a data structure that represents a set of points included in a multidimensional space, and includes: a search unit () that, when a particular multidimensional region is specified as a query region, specifies regions that are expressed as portions shared between regions starting with feature value prefixes and regions starting with coordinate prefixes with respect to respective dimensions, and that are included in the query region, and outputs selected sections that are sections included in a data structure corresponding to the specified regions, the feature value prefixes being prefixes obtained from bit representations of feature values of the points, and the coordinate prefixes being prefixes obtained from bit representations of coordinates of the points with respect to a particular dimension; and an aggregation unit () that calculates information regarding a set of points included in the query region, by using the selected sections.

Information processing device, information processing method, and computer-readable storage medium

[Problem] To suppress increases in the size of a fully indexable dictionary while making it possible for a target bit stream to be subjected to two types of selection operation employing the fully indexable dictionary. [Solution] An information processing device () is provided with a storage unit () which stores a data structure () used to represent a bit stream formed using a first value and a second value. The data structure () includes: first data specifying the positions on the bit stream of all or some succession segments including a succession of one or more of the first value or the second value; second data specifying, for some of the succession segments, the number of first values that have appeared on the bit stream from the beginning of the bit stream as far as the succession segment; and third data specifying, for some of the succession segments, the number of second values that have appeared on the bit stream from the beginning of the bit stream as far as the succession segment.

Data structure, information processing device, information processing method, and program recording medium

To provide an input assistance device, an input assistance method and a storage medium which can present a character string to be suggested to a user in consideration of a probability of being inputted first in a character string. An input assistance device is for assisting a user to input a character string, the device includes: a character string determining unit that determines a character string to be suggested relating to the inputted kana character string, in the case that a user inputs a kana character string by use of index structure, the index structure recording therein a word together with its kana-reading and the index structure indicating whether or not it is probable that the word is inputted first at a time of inputting a character string; and a suggested candidate presenting unit that presents the character string to be suggested, which is determined, as a suggested candidate.

Input assistance device, input assistance method and storage medium

Described are a reputation analysis device, reputation analysis method, and reputation analysis-use program capable of suitably analyzing temporal changes in reputation for an object indicated by a keyword. The disclosed reputation analysis device is provided with a voluntary activity description extraction means for extracting descriptions representing voluntary activity related to an object indicated by a keyword that has been input from within a plurality of documents; and a reputation chronological data estimation means for counting the number of occurrences of voluntary activity at each time point wherein the voluntary activity expressed by a description representing the voluntary activity related to the object has been performed, and estimating reputation chronological data for chronologically representing evaluations for the object by the agents of the voluntary activity.

Reputation analysis system and reputation analysis method

A document analysis device () comprises a common assessment information selection unit () and an event impact analysis unit (). The common assessment information selection unit () identifies information that matches second assessment information that appears in event-related documents which include descriptions concerning a designated specific event, from among first assessment information that appears in documents for analysis which include descriptions relating to items for analysis, and classifies the information thus identified as common assessment information. The event impact analysis unit () counts the number of times the common assessment information appears in the documents that are generated prior to the event occurring, and the number of times the common assessment information appears in the documents for analysis that are generated subsequent to the event occurring, and derives an index that denotes the impact of the specific event upon the documents for analysis, on the basis of the results of the counts thereupon.

Growing community of inventors

Tokyo, Japan

Yuzuru Okajima