Abstract: A system and method for automatically tagging customer messages using artificial intelligence models. A server gateway processes the customer messages via an artificial intelligence system featuring artificial intelligence models. The artificial intelligence system analyzes the customer messages to determine the content by tagging words and phrases with industry specific tags (e.g. product feedback, product defects, shipping delays, etc) as well as tags based on sentiment type (e.g., negative, positive, neutral, sarcasm, mixed) and contact type (e.g., delivery person, influencer, postsale, presale). The artificial intelligence system returns the tagged results, which are transmitted by the server gateway to a user computational device or another system for visualization.

Abstract: A computer-implemented method, computer program product, and computing system for rendering an annotatable image within an image viewer. An indication of an intent to annotate the annotatable image is received from a user. A meme generation interface is rendered with respect to the annotatable image. Meme annotation criteria is received from the user via the meme generation interface. The meme annotation criteria includes one or more of: a meme message, a meme position indicator, and a font type identifier. The annotatable image is modified based, at least in part, upon the meme annotation criteria, thus generating an annotated image. The annotated image is published to a meme publication website.

Abstract: Embodiments described herein provide methods and systems for effectively and efficiently summarizing long documents. A transformer is provided with bottom-up and top-down inference combined to effectively capture long-range dependency. In the bottom-up inference, each token only attends to nearby tokens within a window of a specified size. In the top-down inference, full self-attention is given using units with coarser granularity. The bottom-up-inferred token representations are then updated with the top-down representations, which is achieved with cross-attention between the top and token levels. Multiple levels of top-down representations with increasingly coarser granularity can be used if documents are extremely long.

Abstract: A semantic document generation and search system is described. The semantic document extraction system generates a knowledge graph representing a collection of documents, each document being represented as a sub-graph of the knowledge graph being linked to each other by common terms of a plurality of document terms. The system extracts a first filter criterion based on the plurality of terms of the sub-graphs representing the collection of documents, receives a first search value for the first filter criterion, and identifies a subset of sub-graphs, of the knowledge graph, that include a term corresponding to the first filter criterion and having a term value corresponding to the first search value. The system prunes the knowledge graph to include only the identified subset of sub-graphs, and extracts and outputs a subset of the collection of documents corresponding to the subset of sub-graphs included in the pruned knowledge graph.

Abstract: A user interface comprising a set of comments that are aggregated from and included in a plurality of collaborative documents provided by a cloud-based content management platform are displayed. Each of the plurality of collaborative documents is a separate data file. A modification to a comment of the set of comments is received based on user input via the user interface displaying the set of comments included in the plurality of collaborative documents. Responsive to receiving the modification to the comment of the set of comments based on the user input via the user interface displaying the set of comments included in the plurality of collaborative documents, the user interface is updated to reflect the modified comment of the set of comments.

Abstract: The present disclosure provides systems and methods for relationship extraction. Embodiments of the present disclosure provide a relationship extraction network trained to identify relationships among entities in an input text. The relationship extraction network is used to generate a dependency path between entities in an input phrase. The dependency path includes a set of words that connect the entities, and is used to predict a relationship between the entities. In some cases, the dependency path is related to a syntax tree, but it may include additional words, and omit some words from a path extracted based on a syntax tree.

Abstract: A method for marking text in digital typography includes identifying one or more glyphs that intersect or overlap with a text marking bounding box, drawing a modified text marking to avoid intersecting with the one or more glyphs, and causing a display device to display the modified text marking with the text. The text marking is associated with a line of text including the glyphs or adjacent to a waxline of text including the glyphs. For each of the glyphs, the glyph corresponding to the glyph bounding box intersecting with the text marking is indicated. The modified text marking is drawn based on outlines of the glyphs, intersections between a text marking bounding box and the glyph outlines, and a user-specified glyph offset, text marking weight, and/or text marking offset to avoid intersecting with the glyphs. The shape of the modified text marking avoids intersecting with or overlapping the glyph.

Abstract: A real-time conversation is monitored between a user and an intelligent virtual assistant (IVA). A visualization may be generated and displayed to the user on the user computing device based on one or more topics identified in the conversation. The conversation between the user and the IVA may continue and is continued to be monitored. The visualization can be updated as the conversation continues, e.g., based on further topics being identified.

Abstract: A screen data generating system (100) includes: a generation device (10) to generate screen data for displaying a monitoring screen (101) used for monitoring an operating state of a control device (30) that controls an apparatus (40); and a server (20) to acquire, from the control device (30), device identification information for identifying the control device (30) and unit configuration information about a unit included in the control device (30) to provide the acquired device identification information and the acquired unit configuration information. The generation device (10) includes a template storage to store multiple templates of the screen data, and generates, from a template including the unit configuration information provided by the server (20), the screen data relating to the control device indicated by the device identification information provided by the server (20).

Abstract: Generally discussed herein are devices, systems, and methods for generating an embedding that is both local string dependent and global string dependent. The generated embedding can improve machine learning (ML) model performance. A method can include converting a string of words to a series of tokens, generating a local string-dependent embedding of each token of the series of tokens, generating a global string-dependent embedding of each token of the series of tokens, combining the local string dependent embedding the global string dependent embedding to generate an n-gram induced embedding of each token of the series of tokens, obtaining a masked language model (MLM) previously trained to generate a masked word prediction, and executing the MLM based on the n-based induced embedding of each token to generate the masked word prediction.

Abstract: Embodiments are disclosed for automatic enhancement of paragraph justification. A method includes receiving a selection of at least one paragraph, determining a plurality of penalty values for at least one typographic feature by varying a typographic feature value, the penalty values indicating a deviation from an optimal layout of the at least one paragraph, determining at least one optimal penalty value for the at least one typographic feature, the at least one optimal penalty value corresponding to at least one optimal typographic feature value of the at least one typographic feature, determining a priority for each of the at least one typographic feature based on a plurality of justification rules and the at least one optimal penalty value, and updating the at least one typographic feature of the at least one paragraph based on the priority and the at least one optimal typographic feature value.

Abstract: Approaches for generating virtual representations of smart objects in a 3D visual programming interface. The interface displays a 3D virtual environment containing virtual objects that represents a real-world environment containing smart objects. The 3D virtual environment displays virtual objects in a manner that is spatially accurate relative to the physical objects in the real-world environment. For each virtual object representing a physical object, a logic node (port node) is displayed, the port node representing the set of functions associated with the physical object. The interface enables users to create, delete, or modify different types of logic nodes (representing functions) and create, delete, or modify links (representing data connections) between logic nodes within the 3D virtual environment. The authoring of the logic nodes and links produces an executable program.

Abstract: An information processing apparatus includes: a storage that stores a template which defines a display form of a ticker; a material data acquisition unit that acquires material data to be displayed on the ticker; a selection unit that selects, on the basis of the contents of the material data acquired by the material data acquisition unit, a template stored in the storage; a production unit that produces ticker data by applying the template selected by the selection unit to the material data acquired by the material data acquisition unit; and a provision unit that provides provision data which includes the ticker data produced by the production unit.

Abstract: Systems, devices, and methods are described herein for providing a graphical user interface for configuring presentations of content and controlling distribution of content, for example, through in conjunction with a management system.

Abstract: A whitelisting approach to redaction may include receiving a normalization request containing a binary file with complex structured data, such as a workbook or spreadsheet file, from an application on a user device through a redaction service provided by an e-discovery platform. In response to the normalization request, a normalization process starts and runs asynchronously to apply a whitelist to the binary file. The whitelist is configurable and specifies features (e.g., data types, workbook object types, etc.) of the binary file that are considered safe by a party to a lawsuit or investigation. The normalization process includes a pre-processing stage, a transferring stage, and a post-processing stage to push all the data to a visible level and produce a normalized document with the whitelisted features. An artifact containing the normalized document can then be generated and used to render a normalized representation for interactive redaction.

Abstract: A dataset captioning system is described that generates captions of text to describe insights identified from a dataset, automatically and without user intervention. To do so, given an input of a dataset the dataset captioning system determines which data insights are likely to support potential visualizations of the dataset, generates text based on these insights, orders the text, processes the ordered text for readability, and then outputs the text as a caption. These techniques also include adjustments made to the complexity of the text, globalization of the text, inclusion of links to outside sources of information, translation of the text, and so on as part of generating the caption.

Abstract: A computer readable medium comprising a plurality of instructions stored thereon that are executable by a computer processor to perform steps to identify a changed element within a target web page is disclosed. A pre-region longest matching segment that matches a pre-region segment of a pre-region of a source web page is identified within a pre-region of the target page. A post-region longest matching segment that matches a post-region segment of a post-region of a source web page is identified within a post-region of the target page. The changed element in the target web page is identified that is between the pre-region longest matching segment and the post-region longest matching segment in response to the pre-region longest matching segment being determined to be within a pre-defined distance of the post-region longest matching segment.

Abstract: Edit automation enhancements may be implemented in source code editors and other text editors. Provisional selections that indicate user intentions are submitted to a suggestion generator with other edit context information, to improve the quality of generated text suggestions and reduce the cognitive load on users. A provisional selection may include a highlighted completion list entry, or document text targeted by a hovering cursor, or metainformation text targeted by the hovering cursor, for example. An inline grey text suggestion driven by provisional selection may be displayed simultaneously with completion list suggestions that were created without regard to provisional selection. Suggestions driven by provisional selection may be interleaved with existing document text. Suggestions may be accepted fully in one gesture, or in parts. Suggestions may be edited by a user before being accepted, driving further suggestion refinement.

Abstract: A webpage containing information to be extracted may undergo changes to a layout of elements that present the information. These changes could result in an inability to retrieve the information later. A first graph is determined that represents elements of a first version of a webpage at a first time. An element in the first graph for which information is being acquired is specified. A relevant portion of the first graph is designated that includes the element and immediate neighbors in the first graph. Later, a second version of the webpage is retrieved, and a second graph of that second version is determined. The relevant portion of the first graph is compared to the second graph. If a match is found, the information of interest is extracted from the specified element of the second graph. This allows extraction of information to proceed even if the layout of elements changes.

Abstract: Systems and methods are directed to providing efficient and fast invocation of concurrent sheet defined functions (SDFs) including dynamic arrays by front-loading the work. At SDF creation time, a SDF cell table, a formula table, and a spill area table are generated. The SDF cell table represents cells from a worksheet that are used for the SDF. The formula table comprises an index of formulas used by the SDF, whereby index identifiers are stored in cells of the SDF cell table. The spill area table comprises an index of spill areas where each dynamic array may automatically spill into. The SDF cell table, formula table, and spill area table are shared between a plurality of invocations of the SDF during invocation time.