International Business Machines Corporation

Tomoka Mochizuki

Lianzi Wen

Tomonori Sugiura

Munehiko Sato

Tomohiro Shioya

Asuka Unno

Wen Lianzi

Takaaki Shiratori

Takehiko Ishii

Tomohiro Shimizu

Masashi Miyazaki

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

A method includes storing, in response to marking by a user of an area of a displayed document, information on the marked area; displaying an icon representing the marked area; conducting the storing operation and the displaying operation for a different area; and creating, in response to an operation by the user for arranging two or more icons to be in contact with each other, a joined icon by joining the icons together; and combining marked areas represented by the two or more respective icons, according to a state of contact. A corresponding computer program product and computer system are also disclosed herein.

Combining and displaying multiple document areas

Methods for presenting an image indicating a position for a person are disclosed. A method includes: determining, by a computing device, at least one free space in a location using at least one camera; determining, using the computing device, a new position for a first person in the location based upon the determined at least one free space in the location; and presenting an image to indicate the determined new position for the first person in the location.

Presenting an image indicating a position for a person in a location the person is waiting to enter

Presenting an image indicating a position for a person

A computer-implemented method for analyzing content written on a board, on which a text and/or a drawing are made, is disclosed. The method includes obtaining content data including a series of images, which captures content being written on the board. The method also includes obtaining utterance data representing a series of utterances, which is associated with the series of the images. The method further includes extracting a section from the series of the utterances based on a change in topics and recognizing a content block for the section from the content data. The content block includes one or more content parts written during the section. The method includes further calculating evaluation value for the content block by using one or more utterances included in the section.

Analysis of content written on a board

Systems for presenting an image indicating a position for a person are disclosed. A system includes: a hardware processor, a computer readable memory, and a computer readable storage medium associated with a computer device; at least one camera; program instructions of a free space determiner configured to determine at least one free space in a location using the at least one camera; program instructions of a new position determiner configured to determine, for a first person in the location, a new position based upon the at least one free space in the location determined by the free space determiner; and program instructions of an image presenter configured to present an image in the location to indicate the new position for the first person in the location determined by the new position determiner.

Aspects of the present invention disclose a method, computer program product, and system for mobile computing device proximity notification. The method includes one or more processors acquiring location information for a plurality of mobile computing devices. The method further includes one or more processors creating a first group of mobile computing devices based on location proximity in the acquired location information of the plurality of mobile computing devices, wherein the created first group includes a first mobile computing device and a second mobile computing device. The method further includes one or more processors determining whether the first mobile computing device is within a predetermined distance to the second mobile computing device, and the first mobile computing device and the second mobile computing device are outside of an area associated with the first group.

Mobile device proximity notification

The accessibility of a hyperlinked files is displayed. A hyperlink that references a resource is extracted from a target file. An attempt to acquire the resource is made by performing a first authentication operation. A first object is received in response to performing the authentication operation. A second object is acquired by performing a second authentication operation using pre-determined authentication information. The first object and the second object are compared to determine if the first object is the same as the second object. Information indicating the accessibility of the resource is presented via a display apparatus.

Displaying the accessibility of hyperlinked files

Information on a cursor or pointer position is obtained, indicating a first content on a document displayed on a screen. A plurality of second contents are retrieved from a history information, each of the second contents comprising the first content. The history information comprises sets of contents, each of the sets comprising a content in the document which was copied by one or more users, and position information of this content. The sets are ranked in a predetermined order. A copy area is proposed based on one or more second contents in the predetermined order among the retrieved second contents.

Proposing a copy area in a document

A computer-implemented method includes identifying a primary code segment, determining a confidence score associated with said primary code segment, and determining whether the confidence score exceeds a confidence threshold. The computer-implemented method further includes responsive to the confidence score exceeding the confidence threshold, determining a logger code segment associated with the primary code segment. A corresponding computer program product and computer system are also disclosed.

Growing community of inventors

Tokyo, Japan

Tomoka Mochizuki