Abstract: The present disclosure provides methods, apparatuses, and systems for managing a virtual session. In some embodiments, the method includes identifying a current activity performed by a user in the virtual session, determining at least one first parameter of the virtual session associated with the current activity, detecting an occurrence of at least one event in a real-world environment, determining a correlation between the at least one event and the at least one first parameter, determining at least one second parameter to be associated with the current activity, based on the correlation, and transforming the virtual session by modifying the at least one first parameter based on the at least one second parameter.

Abstract: A system and a method for continuous monitoring of an entity in an Internet of Things (IoT) environment are provided. The method includes monitoring, using a first sensor among a plurality of sensors at a first location within the IoT environment, a plurality of behaviors associated with the entity at the first location; identifying a second location within the IoT environment and outside a detection range of the first sensor, wherein the second location is associated with a presence of the entity; identifying, based on pre-stored information associated with the IoT environment, a second sensor from the plurality of sensors for monitoring a subset of the plurality of behaviors associated with the entity at the second location; and monitoring, using the second sensor at the second location, the subset of the plurality of behaviors associated with the entity based on one or more trained models.

Abstract: In one embodiment, a method includes receiving a voice input having acoustic features from a first client system associated with a first user, determining emotions associated with the voice input based on one or more of the acoustic features by machine-learning models, determining facial features for a first extended-reality (XR) avatar representing the first user based on the emotions, and sending instructions for rendering the first XR avatar representing the first user to a second client system associated with a second user, wherein the first XR avatar is rendered with the determined facial features.

Abstract: A database management system may include a control plane comprising a memory having computer-readable instructions stored thereon and processor that executes computer-readable instructions to execute one or more services running on the control plane, the control plane connected to a plurality of database servers, wherein each of the plurality of database servers is connected to the control plane via a communication channel, wherein the control plane comprises a plurality of data streams, each of the plurality of data streams configured to communicate messages of a designated type, and wherein the control plane is configured to communicate with a database server of the plurality of database servers using the plurality of data streams and the communication channel associated with the database server and the control plane.

Abstract: A method for Ultra-Wide Band (UWB) based voice assistance to a user by an electronic device is provided. The method includes monitoring over time, by the electronic device, interactions between objects in an environment using at least one UWB sensor of the electronic device, determining, by the electronic device, at least one task and an associated objective of the at least one task corresponding to the monitored interactions, generating, by the electronic device, a semantic description of the at least one task and the associated objective in a natural language (NL) for each object, and providing, by the electronic device, the voice assistance to the user based on the semantic description in the natural language.

Abstract: In one embodiment, a method includes receiving a voice input having acoustic features from a first client system associated with a first user, determining emotions associated with the voice input based on one or more of the acoustic features by machine-learning models, determining facial features for a first extended-reality (XR) avatar representing the first user based on the emotions, and sending instructions for rendering the first XR avatar representing the first user to a second client system associated with a second user, wherein the first XR avatar is rendered with the determined facial features.

Abstract: A system performs named entity recognition for performing natural language processing, for example, for conversation engines. The system uses context information in named entity recognition. The system includes the context of a sentence during model training and execution. The system generates high quality contextual data for training NER models. The system utilizes labeled and unlabeled contextual data for training NER models. The system provides NER models for execution in production environments. The system uses heuristics to determine whether to use a context-based NER model or a simple NER model that does not use context information. This allows the system to use simple NER models when the likelihood of improving the accuracy of prediction based on context is low.

Abstract: The present disclosure provides methods, apparatuses, and systems for managing a virtual session. In some embodiments, the method includes identifying a current activity performed by a user in the virtual session, determining at least one first parameter of the virtual session associated with the current activity, detecting an occurrence of at least one event in a real-world environment, determining a correlation between the at least one event and the at least one first parameter, determining at least one second parameter to be associated with the current activity, based on the correlation, and transforming the virtual session by modifying the at least one first parameter based on the at least one second parameter.

Abstract: A database management system may include a control plane comprising a memory having computer-readable instructions stored thereon and processor that executes computer-readable instructions to execute one or more services running on the control plane, the control plane connected to a plurality of database servers, wherein each of the plurality of database servers is connected to the control plane via a communication channel, wherein the control plane comprises a plurality of data streams, each of the plurality of data streams configured to communicate messages of a designated type, and wherein the control plane is configured to communicate with a database server of the plurality of database servers using the plurality of data streams and the communication channel associated with the database server and the control plane.

Abstract: A natural language processing system that trains task models for particular natural language tasks programmatically generates additional utterances for inclusion in the training set, based on the existing utterances in the training set and the existing state of a task model as generated from the original (non-augmented) training set. More specifically, the training augmentation module 220 identifies specific textual units of utterances and generates variants of the utterances based on those identified units. The identification is based on determined importances of the textual units to the output of the task model, as well as on task rules that correspond to the natural language task for which the task model is being generated. The generation of the additional utterances improves the quality of the task model without the expense of manual labeling of utterances for training set inclusion.

Abstract: A system performs named entity recognition for performing natural language processing, for example, for conversation engines. The system uses context information in named entity recognition. The system includes the context of a sentence during model training and execution. The system generates high quality contextual data for training NER models. The system utilizes labeled and unlabeled contextual data for training NER models. The system provides NER models for execution in production environments. The system uses heuristics to determine whether to use a context-based NER model or a simple NER model that does not use context information. This allows the system to use simple NER models when the likelihood of improving the accuracy of prediction based on context is low.

Abstract: A system performs named entity recognition for performing natural language processing, for example, for conversation engines. The system uses context information in named entity recognition. The system includes the context of a sentence during model training and execution. The system generates high quality contextual data for training NER models. The system utilizes labeled and unlabeled contextual data for training NER models. The system provides NER models for execution in production environments. The system uses heuristics to determine whether to use a context-based NER model or a simple NER model that does not use context information. This allows the system to use simple NER models when the likelihood of improving the accuracy of prediction based on context is low.

Abstract: A natural language processing system that trains task models for particular natural language tasks programmatically generates additional utterances for inclusion in the training set, based on the existing utterances in the training set and the existing state of a task model as generated from the original (non-augmented) training set. More specifically, the training augmentation module 220 identifies specific textual units of utterances and generates variants of the utterances based on those identified units. The identification is based on determined importances of the textual units to the output of the task model, as well as on task rules that correspond to the natural language task for which the task model is being generated. The generation of the additional utterances improves the quality of the task model without the expense of manual labeling of utterances for training set inclusion.

Abstract: A document transcription application receives an image of a document that comprises structured data. The document transcription application performs optical character recognition upon the image of the document to produce a block of text. The document transcription application applies the block of text to a first machine learning model to determine a heat map for a class of data in the structured data in the image of the document. The document transcription application applies the image of the document and the heat map to a second machine learning model to identify a region of the image of the document representing the class of data. The document transcription application generates, using the identified region and the block of text, a structured data file.