Abstract: This document relates to natural language processing using a framework such as a neural network. One example method involves obtaining a first document and a second document and propagating attention from the first document to the second document. The example method also involves producing contextualized semantic representations of individual words in the second document based at least on the propagating. The contextualized semantic representations can provide a basis for performing one or more natural language processing operations.

Abstract: A method, system, and computer program product are configured to: create a link tracing data structure in response to receiving a request from a user interface (UI), wherein the link tracing data structure includes a synchronization identifier and information about user actions in the UI; handle the request by calling plural microservices; add respective synchronization content for each one of the plural microservices to the link tracing data structure, wherein the respective synchronization content for a respective one of the plural microservices comprises: the synchronization identifier; a respective step identifier that identifies the respective one of the plural microservices; and a respective synchronization message that describes an execution status of the respective one of the plural microservices; store the link tracing data structure; and provide the link tracing data structure to a requesting user.

Abstract: A computer-implemented technique is described herein for assisting a user in advancing a task objective. The technique uses a suggestion-generating system (SGS) to provide one or more suggestions to a user in response to at least a last-submitted query provided by the user. The SGS may correspond to a classification-type or generative-type neural network. The SGS uses a machine-trained model that is trained using a multi-task training framework based on plural groups of training examples, which, in turn, are produced using different respective example-generating methods. One such example-generating method constructs a training example from queries in a search session. It operates by identifying the task-related intent the queries, and then identifying at least one sequence of queries in the search session that exhibits a coherent task-related intent. A training example is constructed based on queries in such a sequence.

Abstract: Provided is a color wheel. The color wheel includes a substrate, a conversion layer disposed on the substrate for wavelength conversion of incident light and obtaining irradiated laser, a first filter layer for filtering the irradiated laser to obtain a first light for modulating an image in a first color gamut range, and a second filter layer for filtering the irradiated laser to obtain a second light for modulating an image in a second color gamut range. Planes, in which the light incident surface of the conversion layer, the light incident surface of the first filter layer and the light incident surface of the second filter layer are located respectively, are parallel or coincide with each other.

Abstract: Methods, systems, and media for storing entries in and/or retrieving information from an object memory are provided. In some examples, a content item is received that has content data. The content data associated with the content item may be provided to one or more semantic models that generate semantic objects. From one or more of the semantic models, one or semantic objects may be received. The one or more semantic objects may then be inserted into the object memory. The semantic objects may be associated with respective indications corresponding to a reference to source data associated with the semantic objects. Further, the insertion may trigger a memory storage operation to store the semantic objects. A plurality of collections of stored objects may be received from the object memory, based on a provided input, to determine a result.

Abstract: The present disclosure relates to generating semantic search engine results. Aspects of the present disclosure retrieve relevant information from a search engine based on user's search query. The query can be a classic search query (keyword or short phrase) or a conversational query (e.g., a chat messages between users and/or chatbots), a query based upon an email or other type of message, or a query generate based upon a content item (e.g., a webpage, image, video, document, etc.). Aspects of the disclosure leverage a large language model (LLM), such as, for example, a generative model, to summarizes the content according to the intent detected from the query. In some cases, aspects of the present disclosure may generate a direct answer to the query and provide relevant references to support the information.

Abstract: A computing system is disclosed that includes a processor and memory. The memory stores instructions that, when executed by the processor, cause the processor to perform several acts. The acts include receiving, by a generative model, input set forth by a user of a client computing device that is in network communication with the computing system. The acts also include generating, by the generative model, a query based upon the input set forth by the user; providing the query to a search engine. The acts further include receiving, by the generative model and from the search engine, content identified by the search engine based upon the query. The acts additionally include generating, by the generative model, an output based upon a prompt, where the prompt includes the content identified by the search engine based upon the query. The acts also include transmitting the output to the client computing device for presentment to the user.

Abstract: A method, system, and computer program product for data reorganization and logs reorganization. The method includes receiving, by one or more processing units, original data. The method also includes classifying, by the one or more processing units, the original data into different types based on a trained type classification model. The method also includes generating, by the one or more processing units, at least one severity for at least part of the original data based on a trained severity classification model, the at least part of the original data corresponding to at least one type. The method also includes outputting, by the one or more processing units, at least one message, the at least one message indicating the severity of the at least part of the original data.

Abstract: This document relates to natural language processing using a framework such as a neural network. One example method involves obtaining a first document and a second document and propagating attention from the first document to the second document. The example method also involves producing contextualized semantic representations of individual words in the second document based at least on the propagating. The contextualized semantic representations can provide a basis for performing one or more natural language processing operations.

Abstract: A computer-implemented technique is described herein for assisting a user in advancing a task objective. The technique uses a suggestion-generating system (SGS) to provide one or more suggestions to a user in response to at least a last-submitted query provided by the user. The SGS may correspond to a classification-type or generative-type neural network. The SGS uses a machine-trained model that is trained using a multi-task training framework based on plural groups of training examples, which, in turn, are produced using different respective example-generating methods. One such example-generating method constructs a training example from queries in a search session. It operates by identifying the task-related intent the queries, and then identifying at least one sequence of queries in the search session that exhibits a coherent task-related intent. A training example is constructed based on queries in such a sequence.

Abstract: A computer-implemented technique is described herein for assisting a user in advancing a task objective. The technique uses a suggestion-generating system (SGS) to provide one or more suggestions to a user in response to at least a last-submitted query provided by the user. The SGS may correspond to a classification-type or generative-type neural network. The SGS uses a machine-trained model that is trained using a multi-task training framework based on plural groups of training examples, which, in turn, are produced using different respective example-generating methods. One such example-generating method constructs a training example from queries in a search session. It operates by identifying the task-related intent the queries, and then identifying at least one sequence of queries in the search session that exhibits a coherent task-related intent. A training example is constructed based on queries in such a sequence.

Abstract: Method, systems, and computer program products for access configuration in hybrid network environments are disclosed. According to the method, an access configuration request is received from a client device in a first network environment, wherein the access configuration request is associated with an access to a network resource in a second network environment and comprises first authentication information associated with the client device. Further, second authentication information associated with the network resource is obtained. The first and second authentication information is further used to determine whether the access configuration request is verified. If the access configuration request is verified, connectivity between the client device and the network resource can be automatically established.

Abstract: A driver for driving an LED light engine of an LED tube is provided. The driver includes (I) a first driver unit including an input stage for connecting to a power supply, an output stage for connecting to the LED light engine, and a power converter stage for converting input power from AC mains or a CCG (electromagnetic control gear) into an output power for driving the LED light engine and (II) a second driver unit including an input stage for connecting to a power supply, an output stage for connecting to the LED light engine, and a power converter stage for converting input power from an ECG (electronic control gear) into an output power for driving the LED light engine. The two driver units are alternatively activatable for driving the LED light engine depending on when the LED tube is connected to AC mains, a CCG, or an ECG.

Abstract: A method, system, and computer program product for data reorganization and logs reorganization. The method includes receiving, by one or more processing units, original data. The method also includes classifying, by the one or more processing units, the original data into different types based on a trained type classification model. The method also includes generating, by the one or more processing units, at least one severity for at least part of the original data based on a trained severity classification model, the at least part of the original data corresponding to at least one type. The method also includes outputting, by the one or more processing units, at least one message, the at least one message indicating the severity of the at least part of the original data.

Abstract: This document relates to natural language processing using a framework such as a neural network. One example method involves obtaining a first document and a second document and propagating attention from the first document to the second document. The example method also involves producing contextualized semantic representations of individual words in the second document based at least on the propagating. The contextualized semantic representations can provide a basis for performing one or more natural language processing operations.

Abstract: This document relates to natural language processing using a framework such as a neural network. One example method involves obtaining a first document and a second document and propagating attention from the first document to the second document. The example method also involves producing contextualized semantic representations of individual words in the second document based at least on the propagating. The contextualized semantic representations can provide a basis for performing one or more natural language processing operations.

Abstract: A wavelength conversion device and a light-emitting device and a projection device using the wavelength conversion device are provided. The wavelength conversion device includes a substrate capable of rotating around a rotating shaft, the substrate includes a first surface and a second surface opposite to each other, and an annular side surface, which is formed between the first surface and the second surface and is not perpendicular to the first surface. The first surface is provided with a wavelength conversion material layer, and the annular side surface includes a first area and a second area. The first area and the second area are used to reflect incident light beams.

Abstract: A wavelength conversion device and a light-emitting device and a projection device using the wavelength conversion device are provided. The wavelength conversion device includes a substrate capable of rotating around a rotating shaft, the substrate includes a first surface and a second surface opposite to each other, and an annular side surface, which is formed between the first surface and the second surface and is not perpendicular to the first surface. The first surface is provided with a wavelength conversion material layer, and the annular side surface includes a first area and a second area. The first area and the second area are used to reflect incident light beams.

Abstract: Provided is a color wheel. The color wheel includes a substrate, a conversion layer disposed on the substrate for wavelength conversion of incident light and obtaining irradiated laser, a first filter layer for filtering the irradiated laser to obtain a first light for modulating an image in a first color gamut range, and a second filter layer for filtering the irradiated laser to obtain a second light for modulating an image in a second color gamut range. Planes, in which the light incident surface of the conversion layer, the light incident surface of the first filter layer and the light incident surface of the second filter layer are located respectively, are parallel or coincide with each other.

Abstract: A computer-implemented technique is described herein for assisting a user in advancing a task objective. The technique uses a suggestion-generating system (SGS) to provide one or more suggestions to a user in response to at least a last-submitted query provided by the user. The SGS may correspond to a classification-type or generative-type neural network. The SGS uses a machine-trained model that is trained using a multi-task training framework based on plural groups of training examples, which, in turn, are produced using different respective example-generating methods. One such example-generating method constructs a training example from queries in a search session. It operates by identifying the task-related intent the queries, and then identifying at least one sequence of queries in the search session that exhibits a coherent task-related intent. A training example is constructed based on queries in such a sequence.