A method and system for inserting hand-written text is disclosed. The method includes detecting, from a stylus, an insertion gesture on a touch screen, determining, on the touch screen, an insertion location where the hand-written text is to be inserted, generating, on the touch screen, an insertion box for receiving the hand-written text from the stylus, detecting, from the stylus, the hand-written text in the insertion box, and, in response to determining that the hand-written text nears or exceeds a boundary of the insertion box, increasing a size of the insertion box to accommodate the hand-written text. The method further includes detecting, from the stylus, a completion gesture on the touch screen, reducing the size of the insertion box to encapsulate the inserted hand-written text, and erasing the insertion box and inserting the hand-written text into a space previously occupied by the insertion box.

The present disclosure relates to a method of evaluating accuracy of a summary of a document. The method includes receiving a plurality of reference summaries of a document and a system summary of the document. The system summary is generated by a machine. The method further includes extracting, for each reference summary, a tuple that is a pair of words composed of a modified word and a dependent word having a dependency relation to the modified word and a label representing the dependency relation. The method further includes replacing, for each of the extracted tuples, each of the modified word of the tuple's word pair and the dependent word with a class predetermined for the words. The method further generates a score of the system summary based on the class and a set of tuples of the system summary.

An object recognition device including an artificial neural network (NN) engine configured to receive learning data and weights, make an object recognition model (ORM) learn by using the received information, and provide selected weight data including weights from the selected portion of the weights, and further configured to receive a feature vector, and apply the feature vector extracted from an object data that constructs the object and the selected weight data to the learned ORM to provide an object recognition result, a nonvolatile memory (NVM) configured to store the learned ORM, and an error correction code (ECC) engine configured to perform an ECC encoding on the selected weight data to generate parity data, provide the selected weight data and the parity data to the NVM, and provide the selected weight data to the NN engine by performing an ECC decoding on the selected weight data based on the parity data.

An object recognition device including an artificial neural network (NN) engine configured to receive learning data and weights, make an object recognition model (ORM) learn by using the received information, and provide selected weight data including weights from the selected portion of the weights, and further configured to receive a feature vector, and apply the feature vector extracted from an object data that constructs the object and the selected weight data to the learned ORM to provide an object recognition result, a nonvolatile memory (NVM) configured to store the learned ORM, and an error correction code (ECC) engine configured to perform an ECC encoding on the selected weight data to generate parity data, provide the selected weight data and the parity data to the NVM, and provide the selected weight data to the NN engine by performing an ECC decoding on the selected weight data based on the parity data.

A method includes tracking handwritten letter input with a human interface device, inking the handwritten letter input, identifying the letters and displaying at least one suggested word in-line with the inking. The suggested word is based on the letters identified.

Techniques are provided for performing sentiment analysis on words in a first data set. An example embodiment includes generating a word embedding model including a first plurality of features. A value indicating sentiment for the words in the first data set can be determined using a convolutional neural network (CNN). A second plurality of features are generated based on bigrams identified in the data set. The bigrams can be generated using a co-occurrence graph. The model is updated to include the second plurality of features, and sentiment analysis can be performed on a second data set using the updated model.

An electronic device is provided. The electronic device includes a memory configured to store a computer executable instructions; and a processor configured to execute the executable instructions to: determine a text corresponding to a received command, provide response information on the command based on a first artificial intelligence model classifying the text as a text corresponding to one of a plurality of pre-stored texts, and provide error information on the command based on the first artificial intelligence model classifying the text as an error, wherein the first artificial intelligence model is configured to classify the text as the error based on the text corresponding to the command being a similar text having one of an entity and an intent different from at least one of the plurality of pre-stored texts.

Digital glyph overlap correction system implemented as part of a computing device is described. The system is configured to improve detection and correction of overlaps of digital glyphs by detecting on overlap of digital glyphs within a digital document, determining a glyph property causing the overlap, determining a change to the parameter of the glyph property that causes the overlap, generating a correction for the overlap based on the change to the parameter, and rendering the digital document as having the correction. The digital glyph overlap correction system corrects or facilitates correction of the overlap in an efficient and seamless manner, thereby improving the aesthetic appeal of content within the digital document.

Digital glyph overlap correction system implemented as part of a computing device is described. The system is configured to improve detection and correction of overlaps of digital glyphs by detecting on overlap of digital glyphs within a digital document, determining a glyph property causing the overlap, determining a change to the parameter of the glyph property that causes the overlap, generating a correction for the overlap based on the change to the parameter, and rendering the digital document as having the correction. The digital glyph overlap correction system corrects or facilitates correction of the overlap in an efficient and seamless manner, thereby improving the aesthetic appeal of content within the digital document.

A system summary can be evaluated with high accuracy. A tuple extraction unit that extracts tuples which are sets of a word pair composed of a head word and a modifier word having a dependency relation and a label indicating the dependency relation for each of a plurality of reference summaries obtained in advance for a summary target document and a system summary generated for the summary target document by a system and replaces each of the head word and the modifier word of the word pair of each of the extracted tuples with a class determined in advance for words. A score calculation unit that calculates a score of the system summary on the basis of a group of tuples of all the plurality of reference summaries and a group of tuples of the system summary, replaced with the classes.