International Business Machines Corporation

Inovys Corporation

Takehiko Ishii

Daisuke Maruyama

Tomoka Mochizuki

Takaaki Shiratori

Kazuo Aoki

Richard C Dokken

Gerald Chan

In a method for improving machine translation results, a processor receives a target document in a first language. A processor may also translate the target document into a first translated document in a second language using a first neural machine translation (NMT) model, determine a target attribute value from the target document and a first translated attribute value for the first translated document using a natural language understanding (NLU) model, and compare the target attribute value to the first translated attribute value to determine a first comparison score for the first NMT model.

Detection and correction of mis-translation

An embodiment includes determining semantic attributes of a bookmark. The embodiment also includes determining respective attribute values for each of the semantic attributes of the bookmark. The embodiment also includes rendering a three-dimensional (3D) virtual space for display to a user, where the virtual space is defined by three orthogonal axes, each associated with a respective one of the semantic attributes. The embodiment also includes displaying a symbol representative of the bookmark in the virtual space. The symbol is positioned in the virtual space at an intersection of perpendicular projections from locations on the three axes corresponding with respective attribute values of the attributes associated with the respective axes.

Attribute-based positioning of bookmarks in a 3D virtual space

An information classification system includes a server including a knowledge base that receives classification information to be classified, conducts language analysis of the classification information to acquire and classify a plurality of keywords into elements made up of a classification target word and a related word that modifies the classification target word, and conducts a search with the related word, so as to assign a classification identification value to the information; a classification candidate extraction section that extracts the classification identification value that the knowledge base assigns to generate an automatic classification result; and a classification update section that receives the automatic classification result and corrects registered items in the knowledge base with a correction value received through a GUI for classification confirmation while referring to log data that is a processing history about automatic classification for the language analysis and the element classification.

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

An information classification system includes a server that includes a knowledge base that receives classification information to be classified, conducts language analysis of the classification information to acquire a plurality of keywords and classify the plurality of keywords into elements made up of a classification target word and a related word that modifies the classification target word, and conduct a search with the related word being for a judgment condition for decision of the classification while separating the classification target word from the related word, so as to assign a classification identification value to the information; a classification candidate extraction section that extracts the classification identification value that the knowledge base assigns to generate an automatic classification result; and a classification update section that receives the automatic classification result, displays a GUI for classification confirmation allowing confirmation of correctness of the automatic classification result, and corrects registered items in the knowledge base with a correction value received through the GUI for classification confirmation while referring to log data that is a processing history about automatic classification for the language analysis and the element classification.

A process for identifying the location of a break in a scan chain in real time as fail data is collected from a tester. Processing a test pattern before applying it on a tester provides a signature enabling a method for a tester to identify a scan cell which is stuck during the time the tester is operating on a device under test rather than accumulating voluminous test data sets for delayed offline analysis.

Growing community of inventors

Yokohama, Japan

Takehiko Ishii