Abstract: A method includes populating a template database with templates associated with template identifiers (IDs) identifying the templates. The method also includes generating a data model that references a template within the template database, where the data model includes a template ID referencing the template in the template database, and where the template includes a parameter field. The data model further includes a template parameter to apply to the parameter field and a digital signature for at least the template ID and the template parameter. The method also includes deploying the data model within a distributed ledger.

Abstract: This disclosure describes one or more implementations of systems, non-transitory computer-readable media, and methods that train a named entity recognition (NER) model with noisy training data through a self-cleaning discriminator model. For example, the disclosed systems utilize a self-cleaning guided denoising framework to improve NER learning on noisy training data via a guidance training set. In one or more implementations, the disclosed systems utilize, within the denoising framework, an auxiliary discriminator model to correct noise in the noisy training data while training an NER model through the noisy training data. For example, while training the NER model to predict labels from the noisy training data, the disclosed systems utilize a discriminator model to detect noisy NER labels and reweight the noisy NER labels provided for training in the NER model.

Abstract: Machine learning recollection techniques are described as part of question answering using a corpus. Inputs are received identifying a search query and a corpus of search data that is to be searched based on the search query. The search query is decomposed to form a plurality of decomposed queries and retrieval search results are generated by searching the corpus of search data using one or more additional terms based on the decomposed queries. A search result is synthesized based on the retrieval search results using a text generation machine-learning model. The search result is presented for display in a user interface.

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: A method includes extracting an action from a document using a machine learning model. The action is associated with an action parameter. The method further includes extracting a plurality of action events corresponding to the action from the document using the machine learning model. The method further includes generating a record associated with the document based on the extracted action. The method further includes populating the record with the action parameter. The method further includes executing an action event in the plurality of action events using the record.

Abstract: Techniques are provided for training graph neural networks with heterophily datasets and generating predictions for such datasets with heterophily. A computing device receives a dataset including a graph data structure and processes the dataset using a graph neural network. The graph neural network defines prior belief vectors respectively corresponding to nodes of the graph data structure, executes a compatibility-guided propagation from the set of prior belief vectors and using a compatibility matrix. The graph neural network predicts predicting a class label for a node of the graph data structure based on the compatibility-guided propagations and a characteristic of at least one node within a neighborhood of the node. The computing device outputs the graph data structure where it is usable by a software tool for modifying an operation of a computing environment.

Abstract: This disclosure describes one or more implementations of systems, non-transitory computer-readable media, and methods that extract viewpoints from content for syntopical reading using an efficient claim-relation graph construction approach. For example, the disclosed systems utilize sentence transformers with claims from content to embed the claims within a metric space (as claim nodes). Furthermore, in some embodiments, the disclosed systems generate a claim relation graph for the claims by utilizing approximate nearest neighbor searches to determine relational edges between a claim node and the claim node's approximate nearest neighbors. Moreover, in some implementations, the disclosed systems utilize the claim relation graph with an edge weighted graph neural network to determine stance labels during extraction of viewpoints (e.g., stance, aspect, and topic) for the claims. Additionally, in one or more instances, the disclosed systems utilize the extracted viewpoints in content retrieval applications (e.g.

Abstract: Embodiments are disclosed for recommending fonts based on text inputs are described. In some embodiments, a method of recommending fonts includes receiving a selection of text, providing a representation of the selection of text to a font recommendation model, generating, by the font recommendation model, a prediction score for each of a plurality of fonts based on the representation of the selection of text, and returning at least one recommended font based on the prediction score for each of the plurality of fonts.

Abstract: A computing system captures image data using a camera and captures spatial information using one or more sensors. The computing system receives voice data using a microphone. The computing system analyzes the voice data to identify a keyword. The computing system analyzes the image data and the spatial information to identify an object corresponding to the keyword. The computing system generates text based on the voice data and the keyword. The computing system stores the text in association with the object. The computing system generates and provides output comprising the text linked to the object or a derivative thereof.

Abstract: System and methods for a text summarization system are described. In one example, a text summarization system receives an input utterance and determines whether the utterance should be included in a summary of the text. The text summarization system includes an embedding network, a convolution network, an encoding component, and a summary component. The embedding network generates a semantic embedding of an utterance. The convolution network generates a plurality of feature vectors based on the semantic embedding. The encoding component identifies a plurality of latent codes respectively corresponding to the plurality of feature vectors. The summary component identifies a prominent code among the latent codes and to select the utterance as a summary utterance based on the prominent code.

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 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: 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: Systems and methods for natural language processing are described. One or more embodiments of the present disclosure identify a claim from a document, wherein the claim corresponds to a topic, create a graph comprising a plurality of nodes having a plurality of node types and a plurality of edges having a plurality of edge types, wherein one of the nodes represents the claim, and wherein each of the edges represents a relationship between a corresponding pair of the nodes, encode the claim based on the graph using a graph convolutional network (GCN) to obtain an encoded claim, classify the claim by decoding the encoded claim to obtain a stance label that indicates a stance of the claim towards the topic, and transmit information indicating a viewpoint of the document towards the topic based on the stance label.

Abstract: Systems and methods for document classification are described. Embodiments of the present disclosure generate classification data for a plurality of samples using a neural network trained to identify a plurality of known classes; select a set of samples for annotation from the plurality of samples using an open-set metric based on the classification data, wherein the annotation includes an unknown class; and train the neural network to identify the unknown class based on the annotation of the set of samples.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that generate a digital document hierarchy comprising layers of parent-child element relationships from the visual elements. For example, for a layer of the layers, the disclosed systems determine, from the visual elements, candidate parent visual elements and child visual elements. In addition, for the layer of the layers, the disclosed systems generate, from the feature embeddings utilizing a neural network, element classifications for the candidate parent visual elements and parent-child element link probabilities for the candidate parent visual elements and the child visual elements. Moreover, for the layer, the disclosed systems select parent visual elements from the candidate parent visual elements based on the parent-child element link probabilities. Further, the disclosed systems utilize the digital document hierarchy to generate an interactive digital document from the digital document image.

Abstract: A method includes populating a template database with templates associated with template identifiers (IDs) identifying the templates. The method also includes generating a data model that references a template within the template database, where the data model includes a template ID referencing the template in the template database, and where the template includes a parameter field. The data model further includes a template parameter to apply to the parameter field and a digital signature for at least the template ID and the template parameter. The method also includes deploying the data model within a distributed ledger.

Abstract: Systems and methods for data augmentation are described. Embodiments of the present disclosure receive a dataset that includes a plurality of nodes and a plurality of edges, wherein each of the plurality of edges connects two of the plurality of nodes; compute a first nonnegative matrix representing a homophilous cluster affinity; compute a second nonnegative matrix representing a heterophilous cluster affinity; compute a probability of an additional edge based on the dataset using a machine learning model that represents a homophilous cluster and a heterophilous cluster based on the first nonnegative matrix and the second nonnegative matrix; and generate an augmented dataset including the plurality of nodes, the plurality of edges, and the additional edge.

Abstract: Systems and methods for document classification are described. Embodiments of the present disclosure generate classification data for a plurality of samples using a neural network trained to identify a plurality of known classes; select a set of samples for annotation from the plurality of samples using an open-set metric based on the classification data, wherein the annotation includes an unknown class; and train the neural network to identify the unknown class based on the annotation of the set of samples.