Abstract: A method, apparatus, non-transitory computer readable medium, and system for document retrieval include obtaining a query and a document. A prompt generator generates a prompt for a reasoning model based on the query and the document. The reasoning model generates a reasoning result based on the prompt. In some cases, the reasoning result indicates that the document answers the query. A machine learning model provides the document in response to the query based on the reasoning result.

Abstract: Embodiments provide systems, methods, and computer storage media for a Nonsymmetric Determinantal Point Process (NDPPs) for compatible set recommendations in a setting where data representing entities (e.g., items) arrives in a stream. A stream representing compatible sets of entities is received and used to update a latent representation of the entities and a compatibility distribution indicating likelihood of compatibility of subsets of the entities. The probability distribution is accessed in a single sequential pass to predict a compatible complete set of entities that completes an incomplete set of entities. The predicted complete compatible set is provided a recommendation for entities that complete the incomplete set of entities.

Abstract: Systems and methods for generating hierarchical queries from text queries are described. Embodiments are configured to encode a text query to obtain a text embedding. Then, embodiments select a field of a data schema by comparing the text embedding to a field embedding corresponding to the field. Subsequently, embodiments generate a hierarchical query including a value corresponding to the selected field. Some embodiments further include one or more formatting models configured to format values included in the text query.

Abstract: Methods and systems are provided for using generative artificial intelligence to evaluate fine-tuned language models. In embodiments described herein, natural language text snippets are generated via a generative language model based on corresponding data. A language model is fine-tuned into a fine-tuned language model via a language model fine-tuning component using the natural language text snippets and the corresponding data as training data. Independent natural language text snippets are generated via the generative language model based on the corresponding data. Each independent natural language text snippet is different than each corresponding natural language text snippet. An evaluation metric of the fine-tuned language model is generated via an evaluation component based on the independent natural language text snippets and the corresponding data.

Abstract: Graphic visualizations, such as charts or graphs conveying data attribute values, can be generated based on natural language queries, i.e., natural language requests. To do so, a natural language request is parsed into n-grams, and from the n-grams, word embeddings are determined using a natural language model. Data attributes for the graphic visualization are discovered in the vector space from the word embeddings. The type of graphic visualization can be determined based on a request intent, which is determined using a trained intent classifier. The graphic visualization is generated to include the data attribute values of the discovered data attributes, and in accordance with the graphic visualization type.

Abstract: Graphic visualizations, such as charts or graphs conveying data attribute values, can be generated based on natural language queries, i.e., natural language requests. To do so, a natural language request is parsed into n-grams, and from the n-grams, word embeddings are determined using a natural language model. Data attributes for the graphic visualization are discovered in the vector space from the word embeddings. The type of graphic visualization can be determined based on a request intent, which is determined using a trained intent classifier. The graphic visualization is generated to include the data attribute values of the discovered data attributes, and in accordance with the graphic visualization type.

Abstract: Systems and methods for data analysis are described. Embodiments of the present disclosure data analysis include displaying, via a data analysis interface, a data visualization in a first region of the data analysis interface; and displaying, via the data analysis interface, an analysis thread visualization in a second region of the data analysis interface. The analysis thread visualization depicts an analysis thread graph including a first node corresponding to the data visualization and an edge corresponding to an analysis path between the first node and a second node.

Abstract: A method, apparatus, and non-transitory computer readable medium for hypergraph processing are described. Embodiments of the present disclosure obtain, by a hypergraph component, a hypergraph that includes a plurality of nodes and a hyperedge, wherein the hyperedge connects the plurality of nodes; perform, by a hypergraph neural network, a node hypergraph convolution based on the hypergraph to obtain an updated node embedding for a node of the plurality of nodes; and generate, by the hypergraph component, an augmented hypergraph based on the updated node embedding.

Abstract: Techniques discussed herein generally relate to applying machine-learning techniques to design documents to determine relationships among the different style elements within the document. In one example, hypergraph model is trained on a corpus of hypertext markup language (HTML) documents. The trained model is utilized to identifying one or more candidate style elements for a candidate fragment and/or a candidate fragment. Each of the candidates are scored, and at least a portion of the scored candidates are presented as design options for generating a new document.

Abstract: Methods, computer systems, computer-storage media, and graphical user interfaces are provided for facilitating generation and presentation of insights. In one implementation, a set of data is used to generate a data visualization. A candidate insight associated with the data visualization is generated, the candidate insight being generated in text form based on a text template and comprising a descriptive insight, a predictive insight, an investigative, or a prescriptive insight. A set of natural language insights is generated, via a machine learning model. The natural language insights represent the candidate insight in a text style that is different from the text template. A natural language insight having the text style corresponding with a desired text style is selected for presenting the candidate insight and, thereafter, the selected natural language insight and data visualization are providing for display via a graphical user interface.

Abstract: Various embodiments describe techniques for making inferences from graph-structured data using graph convolutional networks (GCNs). The GCNs use various pre-defined motifs to filter and select adjacent nodes for graph convolution at individual nodes, rather than merely using edge-defined immediate-neighbor adjacency for information integration at each node. In certain embodiments, the graph convolutional networks use attention mechanisms to select a motif from multiple motifs and select a step size for each respective node in a graph, in order to capture information from the most relevant neighborhood of the respective node.

Abstract: Systems and methods for data analysis are described. Embodiments of the present disclosure data analysis include displaying, via a data analysis interface, a data visualization in a first region of the data analysis interface; and displaying, via the data analysis interface, an analysis thread visualization in a second region of the data analysis interface. The analysis thread visualization depicts an analysis thread graph including a first node corresponding to the data visualization and an edge corresponding to an analysis path between the first node and a second node.

Abstract: A system and methods for providing human-invisible AR markers is described. One aspect of the system and methods includes identifying AR metadata associated with an object in an image; generating AR marker image data based on the AR metadata; generating a first variant of the image by adding the AR marker image data to the image; generating a second variant of the image by subtracting the AR marker image data from the image; and displaying the first variant and the second variant of the image alternately at a display frequency to produce a display of the image, wherein the AR marker image data is invisible to a human vision system in the display of the image.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating naturally phrased insights about data charts using light language models distilled from large language models. To synthesize training data for the light language model, in some embodiments, the disclosed systems leverage insight templates for prompting a large language model for generating naturally phrased insights. In some embodiments, the disclosed systems anonymize and augment the synthesized training data to improve the accuracy and robustness of model predictions. For example, the disclosed systems anonymize training data by injecting noise into data charts before prompting the large language model for generating naturally phrased insights from insight templates. In some embodiments, the disclosed systems further augment the (anonymized) training data by splitting or partitioning data charts into folds that act as individual data charts.

Abstract: Aspects of a method, apparatus, non-transitory computer readable medium, and system include obtaining a document and a query. A plurality of data elements are identified from the document by locating a plurality of corresponding flexible anchor elements. Then, the data elements are extracted based on the plurality of flexible anchor elements. Content including an analysis of the extracted data elements based on the query is generated.

Abstract: Systems and methods for natural language processing are described. Embodiments of the present disclosure obtain a chart and a query via a user interface. An answer model generates an answer to the query based on the chart, wherein the answer model comprises a machine learning model trained based on chart data for the chart. A description model generates a visual description based on the answer and the chart, wherein the description model comprises a machine learning model trained based on a chart specification for the chart. A response component transmits a response to the query based on the answer and the visual description.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for building time-decayed line graphs from temporal graph networks for efficiently and accurately generating time-aware recommendations. For example, the time-decayed line graph system creates a line graph of the temporal graph network by deriving interaction nodes from temporal edges (e.g., timed interactions) and connecting interactions that share an endpoint node. Then, the time-decayed line graph system determines the edge weights in the line graph based on differences in time between interactions, with interactions that occur closer together in time being connected with higher weights. Notably, by using this method, the derived time-decayed line graph directly represents topological proximity and temporal proximity. Upon generating the time-decayed line graphs, the system performs downstream predictive modeling such as predicted edge classifications and/or temporal link predictions.

Abstract: Aspects of the method, apparatus, non-transitory computer readable medium, and system include obtaining a document and an information element. The aspects further include identifying, from the document, an anchor element that has an anchor type and a relationship type, wherein the anchor type describes a structure of a set of anchor elements, and the relationship type describes a relationship between the anchor element and the information element. The aspects further include extracting information corresponding to the information element based on the anchor element, the anchor type, and the relationship type, and displaying the extracted information to a user.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media that utilize a graph neural network to generate data recommendations. The disclosed systems generate a digital graph representation comprising user nodes corresponding to users, data attribute nodes corresponding to data attributes, and edges reflecting historical interactions between the users and the data attributes; Moreover, the disclosed systems generate, utilizing a graph neural network, user embeddings for the user nodes and data attribute embeddings for the data attribute nodes from the digital graph representation. In addition, the disclosed systems generate, utilizing a graph neural network, user embeddings for the user nodes and data attribute embeddings for the data attribute nodes from the digital graph representation.

Abstract: In implementations of systems for generating interactive reports, a computing device implements a report system to receive input data describing a dataset and an analytics report for the dataset that depicts a result of performing analytics on the dataset. The report system generates a declarative specification that describes the analytics report in a language that encodes data as properties of graphic objects. Editing data is received describing a user input specifying a modification to the analytics report. The report system modifies the declarative specification using the language that encodes data as properties of graphic objects based on the user input and the dataset. An interactive report is generated based on the modified declarative specification that includes the analytics report having the modification.