Mitsubishi Electric Corporation

Hayato Uchide

Yusuke Koji

Takeyuki Aikawa

Daishin Ito

A semantic relationship learning device includes processing circuitry to acquire positive example data pairs and to generate negative example data pairs by combining the language data, each of the negative example data pairs being formed with language data that are not in the predetermined semantic relationship with each other; to extract feature values from the negative example data pairs; to calculate a similarity level between the feature values; to classify the negative example data pairs into predetermined similarity level ranges or classifies learning-purposed negative example data pairs into predetermined similarity level ranges, thereby generating learning-purposed negative example data sets corresponding to the similarity level ranges; to select a learning-purposed negative example data set from the learning-purposed negative example data sets in an order according to a selection schedule; and to perform a machine learning process by using the selected learning-purposed negative example data set and the positive example data pairs.

Semantic relationship learning device, semantic relationship learning method, and storage medium storing semantic relationship learning program

An information processing device includes an acquisition unit that acquires a plurality of documents and clue information including a plurality of words and a generation processing unit that generates inter-document relationship source information based on the plurality of documents and the clue information, generates high frequency appearance information based on the inter-document relationship source information, generates vicinity appearance information based on the high frequency appearance information, and generates an inter-document relationship table based on the vicinity appearance information.

Information processing device, and generation method

The following units are included: a word search unit searching a database for each of words included in an input word pair; a word vector extracting unit extracting a word vector corresponding to each of the searched words from a word vector database; a character vector converting unit converting characters included in the word pair into a character vector; a feature amount acquiring unit acquiring a feature amount by combining the extracted word vector of each of the words and the character vector generated by converting the characters; and an estimation unit estimating a semantic relation between the words from the acquired feature amount.

Word semantic relation estimation device and word semantic relation estimation method

A search unit () searches an ontology database () for a node set similar to a given word. A template creating unit () creates a template from common properties and nodes possessed by nodes included in the node set that has been searched for. An additional information determining unit () creates a triple by connecting the template to a node having the given word as a name, uses the created triple as display data, and when a triple is given, registers the given triple in the ontology database ().

Ontology creation assistance device

A speech guidance device includes; a guidance object determining unit for outputting a guidance object to which a visual line of a user is guided; a visual recognition object detecting unit for detecting a visual recognition object which the user is viewing from information indicating a direction of the visual line of the user; a difference detecting unit for detecting a difference between an attribute of the visual recognition object and an attribute of the guidance object; a generating unit for generating a guidance sentence including the attribute of the guidance object; and a synthesizing unit for, when there is a difference between the attribute of the guidance object included in the guidance sentence and the attribute of the visual recognition object, synthesizing and outputting speech of the guidance sentence emphasizing a word of the attribute having the difference.

Growing community of inventors

Tokyo, Japan

Hayato Uchide