Abstract: Methods, systems, and computer program products for unsupervised tunable stylized text transformations are provided herein. A computer-implemented method includes identifying amendable portions of input text by processing at least a portion of the input text using at least one neural network; determining stylistic text modifications to the amendable portions of the input text, the text modifications encompassing a set of stylistic parameters, wherein said determining comprises processing at least a portion of the set of stylistic parameters using at least one neural network; generating a stylized output set of text by transforming at least a portion of the input text, wherein said transforming comprises modifying at least one of the amendable portions of the input text via at least one of the stylistic text modifications encompassed by the set of stylistic parameters; and outputting the stylized output set of text to at least one user.

Abstract: A method, computer system, and a computer program product for text data protection is provided. The present invention may include receiving a text data. The present invention may also include identifying a portion of the received text data having a highest impact on a first confidence score associated with a target model prediction. The present invention may further include generating at least one semantically equivalent text relative to the identified portion of the received text data. The present invention may also include determining that the generated at least one semantically equivalent text produces a second confidence score associated with the target model prediction that is less than the first confidence score associated with the target model prediction. The present invention may further include generating a prompt to suggest modifying the identified portion of the received text data using the generated at least one semantically equivalent text.

Abstract: The subject matter described herein relates to table detection in a spreadsheet. According to implementations of the subject matter described herein, there is proposed a solution for determining a table in a spreadsheet. In the solution, respective multiple attributes of multiple cells comprised in the spreadsheet may be extracted. Respective features of the multiple cells may be determined based on the extracted multiple attributes. The multiple cells may be divided into at least one candidate area based on the features. At least one candidate table in the spreadsheet may be determined based on the at least one candidate area. By means of the solution, respective features of the multiple cells comprised in the spreadsheet may be determined based on the respective attributes of the multiple cells, and further, a candidate region where a table might exist may be determined based on the respective features of the multiple cells.

Abstract: Examples of a content alignment system are provided. The system may receive a content record and a content creation requirement. The system may implement an artificial intelligence component to sort the content record into a plurality of objects and for identifying an object boundary for each of the plurality of objects. The system may identify a plurality of images and implement a first cognitive learning operation to identify an image boundary for each of the plurality of images. The system may identify a plurality of exhibits and implement a second cognitive learning operation to identify a data pattern associated with each of the plurality of exhibits. The system may implement a third cognitive learning operation for determining a content creation model by evaluating the plurality of objects, the plurality of images, and the plurality of exhibits. The system may generate a content creation output to resolve the content creation requirement.

Abstract: A document analysis device that includes a memory operable to store a machine learning model configured to receive a sentence as an input and to output a classification identifier that is associated with a sentence type for the received sentence. The device further includes an artificial intelligence (AI) processing engine configured to receive a document comprising text, to sentences within the document, and to classify the sentences using the machine learning model. The AI processing engine is further configured to identify tagging rules for the document and to annotate one or more sentences from the document with a sentence type that matches a sentence type that is identified by the tagging rules for the document.

Abstract: In an approach, a processor trains a model, via a reinforcement learning process, to produce a first action function for relating states of a natural language based response environment to actions applicable to the natural language based response environment.

Abstract: A non-transitory computer-readable storage medium may include instructions stored thereon for propagating changes to copied text. When executed by at least one processor, the instructions may be configured to cause a computing system to at least present copied text within a user interface of the computing system, monitor the user interface for changes to the copied text, receive a change to the copied text, the change including replacing a first instance of a first word, within the copied text, with a first instance of a second word, and in response to receiving the change to the copied text, present a prompt to replace, within the copied text, a second instance of the first word with a second instance of the second word.

Abstract: One embodiment provides a method, including: receiving two documents, one of the two documents having at least one table that includes the same information as a corresponding table in the other of the two documents, wherein (i) one of the two documents comprises the at least one table in an unstructured table representation and (ii) the other of the two documents comprises the at least one table in a structured table representation; identifying text elements within the at least one table in the unstructured table representation; matching the identified text elements with table elements within the at least one table in the structured table representation; and annotating the at least one table in the structured table representation based upon the matches between the table elements and text elements.

Abstract: Techniques for an ink experience with images are discussed herein. In various implementations, an image is displayed via an image management application for viewing and/or editing images. In conjunction with interaction scenarios provided via the application, an inking mode for adding inked annotations to the image is enabled. Input to apply one or more inked annotations to the image is obtained, such as via finger touches on a touchscreen, drawing with a stylus, camera-based gestures, or other natural input mechanisms. Responsive to obtaining the input, data blocks corresponding to the one or more inked annotations are appended to an image file as additional data blocks for the image.

Abstract: Described herein is a system and method for detecting a layout table by a screen reader. Information regarding a document being displayed by an application is received from an application programming interface of a user interface automation system that provides information regarding user interface elements of application and/or the application. The information includes an indication that the document comprises a table. A determination is made as to whether the table is a data table or a layout table based upon the received information using a rule-based heuristic. When it is determined that the table is a layout table, presentation information associated with the layout table can be skipped over, and, cell data content within the layout table provided. Thus, for a determined layout table, the system and method allow the screen reader to act as if the containing table doesn't exist, but still read the content.

Abstract: A system and method is provided that ranks and sorts websites, apps, email, or VR environment content in real-time to increase engagement, CTR, conversions, and revenue. A client applies attributes to sections of the digital content. A server system tracks end user inputs and generates optimized layouts for the digital content, such as a webpage. The document layout is ordered or reorganized before or after the document is delivered to the end user.

Abstract: Systems, methods, and devices enable the display of native and web components of application. Devices are capable of identifying at least one native component and a plurality of web components that includes a first web component and a second web component, wherein the at least one native component and the plurality of web components are configured to be displayed on a user interface screen. Devices are also capable of generating an image of the first web component and an image of the second web component, displaying the at least one native component at a location on the user interface screen that is between the image of the first web component and the image of the second web component.

Abstract: A computer software program for improving electronic spreadsheets to manage and control scenarios. The program provides methods for the user to record specific changes made to selected value of cells in the spreadsheet. Each recorded item can be dragged and re-ordered via a graphical user interface (GUI) to build up a scenario script. The script can be executed whereby the spreadsheet is updated with the recorded items. The method allows complex scenarios to be played back in step by incremental step, modified, re-ordered, corrected, and re-played while generating user-defined output reports & charts detailing each step change. The method provides a detailed information trail of all value changes made to the spreadsheet suitable for an independent third-party review. Different scenario components can be recorded in parallel by multiple users and then merged to produce a complete solution.

Abstract: Systems and methods for displaying hierarchical table headers as disclosed. The systems and methods can include operations performed by a viewer engine. The operations can include detecting a user interaction with a display of a portion of data. The operations can further include determining a second portion of the data to display. The operations can additionally include obtaining data information for the second portion of the data. The data information can include information about headers for the second portion of the data and information about child-parent relationships between the headers. The operations can include determining one or more hierarchical headers for the second portion of the data. The operations can further include rendering a table including the second portion of the data. The operations can additionally include displaying a display depicted the one or more hierarchical headers and a subset of the table including the second portion of the data.

Abstract: A system and process for extracting information from filled form images is described. In one example, the claimed invention first extracts textual information and the hierarchy in a blank form. This information is then used to extract and understand the content of filled forms. In this way, the system does not have to analyze from the beginning each filled form. The system is designed so that it remains as generic as possible. The number of hard-coded rules in the whole pipeline was minimized to offer an adaptive solution able to address the largest number of forms, with various structures and typography. The system is also created to be integrated as a built-in function in a larger pipeline. The form understanding pipeline could be the starting point of any advanced Natural Language Processing application.

Abstract: A server includes a memory and a processor to receive from a client device a screenshot of an application page from an application. The application page includes a form requiring data to be filled in by a user of the client device. A form template is extracted from the screenshot, with the extracted form template not including form field values. The extracted form template is compared to a private form template database for a match. The private form template database includes private form templates from different applications, with each private form template having form field values previously filled in for the user. Form field values from a matched private form template are provided to the client device for the client device to populate the form in the screenshot.

Abstract: A system and method for detecting webpage zones of interest. A method includes receiving at least one webpage analysis request, wherein the received at least one webpage analysis request includes at least one webpage in a website; identifying, in the at least one webpage, at least one zone, wherein the at least one zone is a content element of a webpage; classifying the at least one zone into a category of interest, wherein the classification is based on a trained machine learning model configured to classify DOM elements of the least one webpage, and wherein a category of interest is a category determined based on a functionality of the website; and storing the classification by indicating the category of interest for each zone.

Abstract: A method for generating presentation slides with distilled content including receiving one or more data files as source material for slide generation, obtaining content from the one or more data files for a slide of a slide presentation, identifying a layout template for the slide based on the content, and distilling the content into distilled content to generate a presentation visualization item based on the distilled content. The distilled content may include a subset of the content. The method may also include generating the slide based on the presentation visualization item and the layout template.

Abstract: Methods and servers for generating a modifiable portion of a digital document which has message slots for placement of digital messages are disclosed. The generating being performed during a first selection-round of a plurality of selection-rounds. The method includes, during the first selection-round: providing access to a first combination of originators that are to bid for message slots during the first selection-round. The first combination is selected by limiting (i) the number of originators that are to bid for message slots, and (ii) which combination of originators are to bid for message slots. The method includes acquiring bidding data for the first selection-round. The method includes triggering placement of digital messages in the message slots of the modifiable portion based on the bidding data, and updating data about the first combination of originators for performing a subsequent selection-round.

Abstract: A method utilizes a deep question answering (QA) system to provide an answer, to a certain type of question, that includes an unfamiliar measurement unit. An answer key is utilized to train a DeepQA system to search for passages that answer a certain type of question, where the DeepQA system outputs an answer key value and an answer key measurement unit that is associated with the answer key value. The method identifies a candidate answer that includes a candidate passage containing the answer key value but not the answer key measurement unit, where a candidate passage measurement unit in the candidate passage is associated with the answer key value. The method then matches the answer key measurement unit to the candidate passage measurement unit based on the answer key measurement unit and the candidate passage measurement unit both being associated with the answer key value.