Abstract: Methods are provided, such as a method of interacting with a large language model (LLM), including the step of a processing system using a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, to provide new context data for the LLM, in order to improve the output, such as continuation text output, generated by the LLM in response to a prompt; and such as a method of interacting with a LLM, including the step of providing continuation data generated by the LLM to a processing system that uses a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, in which the processing system is configured to analyse the continuation output generated by the LLM in response to a prompt to enable an improved version of that continuation output to be provided to a user. Related computer systems are provided.

Abstract: Examples provide a large language model confidence scoring post-calibration based on a combination of temperature scaling, softmax denominator top-k probabilities selection, and polynomial regression. A secure machine learning system receives results generated by a machine learning (ML) model, the results including at least one confidence score. The secure ML system identifies at least one challenge in accuracy of the results generated by the ML model configured to perform document processing and understanding.

Abstract: Systems and methods are provided for categorizing a transaction description using natural language processing.

Abstract: Natural language generation technology is disclosed that applies artificial intelligence to structured data to determine content for expression in natural language narratives that describe the structured data. A graph data structure is employed, where the graph data structure comprises a plurality of nodes. Each of a plurality of the nodes (1) represents a corresponding intent so that a plurality of different nodes represent different corresponding intents and (2) is associated with one or more links to one or more of the nodes to define relationships among the intents.

Abstract: Methods and systems for receiving a plurality of documents including short text data and determining a plurality of forward similarity values based on the short text data in each of the plurality of documents, determining a plurality of reverse similarity values based on the short text data in each of the plurality of documents, generating a forward and reverse similarity matrix based on the plurality of forward similarity values and the plurality of reverse similarity values, and generating a plurality of short text similarity based clusters to group the short text data of the plurality of documents based on the forward and reverse similarity matrix.

Abstract: A computing system, computer program product, and computer-implemented method for quantitative comment summarization are provided. The method includes receiving a collection of comments, identifying a set of candidate key points corresponding to the collection of comments, and selecting a subset of key points from the set of candidate key points, wherein the selected subset of key points includes key points that are most salient in the collection of comments. The method also includes automatically mapping each comment within the collection of comments to any corresponding key points within the subset of key points based on a match score between each comment and key point pair, as well as generating a summary including the subset of key points and an absolute number or percentage of the comments mapped to each key point.

Abstract: An apparatus and method for dynamic data synthesis wherein the apparatus receives a first textual data set, displays at least an interface field, populates the at least an interface field with at least an element of the first textual data set, generates a destination-formatted query using the populated at least an interface field, transmits the formatted query to a remote device, receives a second textual data set, outputs a user score and a set of score metadata, generates a comprehensive report, and displays the comprehensive report to the user.

Abstract: Aspects discussed herein may relate to using machine learning models as part of methods and techniques for ingesting, creating, storing, editing, and managing a document. The document may be a legal contract that includes one or more clauses. Among other things, one or more machine learning models may be configured to recognize clauses and/or classifications, or types, of clauses. For example, the one or more generative language models may be used to generate one or more recommended edits to a clause, generate one or more suggested clauses that are missing from the contract, and/or generate one or more suggested locations where a clause may be inserted into or moved within the contract.

Abstract: In non-limiting examples of the present disclosure, systems, methods and devices for determining a language of a text string are presented. A language detection model may be maintained. The language detection model may comprise identities and weights for initial and final consonants, identities and weights for prefixes and suffixes, and identities and weights for vowel sequences, where each identity is derived from a training corpus. The weights may correspond to a frequency of a text unit in the corpus. A text string may be received and a match score between the text string and the language of the language detection model may be determined. The match score may be based on initial and final consonant scores, prefix and suffix scores, and/or vowel sequence scores for each word in the text string. If the match score meets a threshold value a follow-up action associated with the language may be performed.

Abstract: Implementations relate to managing multimedia content that is obtained by large language model(s) (LLM(s)) and/or generated by other generative model(s). Processor(s) of a system can: receive natural language (NL) based input that requests multimedia content, generate a response that is responsive to the NL based input, and cause the response to be rendered. In some implementations, and in generating the response, the processor(s) can process, using a LLM, LLM input to generate LLM output, and determine, based on the LLM output, at least multimedia content to be included in the response. Further, the processor(s) can evaluate the multimedia content to determine whether it should be included in the response. In response to determining that the multimedia content should not be included in the response, the processor(s) can cause the response, including alternative multimedia content or other textual content, to be rendered.

Abstract: Systems, methods and non-transitory computer readable media for prompt-based attribution of generated media contents to training examples are provided. In some examples, a first media content generated using a generative model in response to a first textual input may be received. The generative model may be a result of training a machine learning model using a plurality of training examples. Each training example of the plurality of training examples may include a respective textual content and a respective media content. Properties of the first textual input and properties of the textual contents included in the plurality of training examples may be used to attribute the first media content to a first subgroup of the plurality of training examples. The training examples of the first subgroup may be associated with a source. Further, a data-record associated with the source may be updated based on the attribution.

Abstract: The present document relates to a method of layered encoding of a compressed sound representation of a sound or sound field. The compressed sound representation comprises a basic compressed sound representation comprising a plurality of components, basic side information for decoding the basic compressed sound representation to a basic reconstructed sound representation of the sound or sound field, and enhancement side information including parameters for improving the basic reconstructed sound representation.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an action selection neural network that is used to select actions to be performed by a reinforcement learning agent interacting with an environment. In particular, the actions are selected from a continuous action space and the system trains the action selection neural network jointly with a distribution Q network that is used to update the parameters of the action selection neural network.

Abstract: Disclosed embodiments relate to natural language processing. Techniques can include receiving input text, extracting, from the input text, at least one modifier and aspect pair, receiving data from a knowledgebase, based on the at least one modifier and aspect pair and commonsense data, generate one or more premise embeddings, convert the input text into tokens, generating at least one vector for one or more of the tokens based on an analysis of the tokens, combine the at least one vector with the one or more premise embeddings to create at least one combined vector, and analyze the at least one combined vector wherein the analysis generates an output indicative of a feature of the input text.

Abstract: Disclosed are an interactive information processing method, an electronic device and a storage medium. The method includes establishing a position correspondence between a display text generated based on a multimedia data stream and the multimedia data stream; and presenting the display text and the multimedia data stream corresponding to the display text based on the position correspondence.

Abstract: An electronic apparatus includes a voice receiving unit, a display unit, and a control unit. The control unit is configured to perform control so as to identify the language of a voice input received by the voice receiving unit. In a case where it is determined the identified language, which is a first language, is different from a second language set as a primary language in the electronic apparatus, the control unit is configured to display on the display unit, a message for confirming whether to change the primary language from the second language to the first language in both the first language and the second language.

Abstract: A computerized method for extracting domain specific insights from a corpus of files containing large documents comprising: breaking down large chunks of text into smaller sentences/short paragraphs in a domain specific way, identifying and removing domain noise; identifying the sentence intents of the non-noise sentences; tagging the sentences with other domain specific attributes; defining a semantic ontology using a graph database based on the sentence intents, a multitude of mini-dictionaries and domain attributes; applying a pre-defined ontology to tag documents with domain specific hashtags; and combining the hashtags using machine learning techniques into insights.

Abstract: A content access device uses local audio translation for content presentation. The content access device receives video and first audio data associated with a first language. The content access device uses translation software and/or other automated translation services to translate the first audio data to second audio data associated with a second language. The content access device synchronizes the video with the second audio data and outputs the video and the second audio data for presentation. The first audio data may be audio, text, and so on. The second audio data may be output as audio, text, and so on.

Abstract: In one embodiment, a method includes receiving a user request from a first user at a client system, wherein the user request is associated with a semantic-intent, identifying dialog-intents associated with the user request by the client system based on the semantic-intent and context information associated with the user request, wherein each dialog-intent is a sub-intent of the semantic-intent; determining agents for executing tasks associated with the dialog-intents by the client system, and presenting information returned from the agents responsive to executing the tasks at the client system.

Abstract: A voice recognition apparatus includes a communication part configured to communicate with a voice recognition server, a voice receiver configured to receive a user's voice signal, a storage part configured to store guide information comprising at least an example command for voice recognition; and a controller. The controller is configured to generate a guide image comprising at least a part of the example command, transmit the received user's voice signal to the voice recognition server through the communication part in response to receiving the user's voice signal by the voice receiver, and update the stored guide information based on update information received through the communication part.