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: 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: 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: 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: 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 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: 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.

Abstract: In an embodiment, a programmed computer system implemented via client-server Software as a Service (SaaS) techniques provides an interactive user interface for identifying specific portions of a digital document susceptible for review and improvement. A server computer may receive a representation of a digital document, such as an email, comprising words arranged into sentences arranged into paragraphs. An embodiment may tokenize a set of all sentences comprising the sequence of sentences into a document-specific vocabulary, then compute a corresponding first and second score for each sentence of the sequence of sentences. The first score may represent a calculated probability of semantic importance of the corresponding sentence to an overall meaning of the digital document. The second score may represent a calculated likelihood that the corresponding sentence will be read by a future reader of the digital document. An embodiment may identify key sentences using the first scores and second scores.

Abstract: A data processing apparatus includes a word selection unit configured to select words corresponding to a part-of-speech type targeted for selection from words disassembled from document data, and a generation unit configured to find, for each of the words selected by the word selection unit, a value obtained by weighting the number of occurrences of each of the words or frequency of occurrences of each of the words according to the part-of-speech type of each of the words to generate a vector with a plurality of the values that are found as values of elements.

Abstract: Features are disclosed for training and using a word embedding model configured to receive textual and context data associated with an utterance of a user. A word embedding model can be trained with text data and context data to account for context associated with the text data. The word embedding model can receive an input vector including text data and one or more sets of context data associated with the text data and perform word embedding based on the input vector. In some embodiments, the input vector can include an automatic speech recognition (“ASR”) confidence score generated by an ASR model and one or more labels generated by an NLU model. In some embodiments, the input vector can include user information associated with the user.

Abstract: Apparatuses, arrangements and methods therein for generation of comfort noise are disclosed. In short, the solution relates to exploiting the spatial coherence of multiple input audio channels in order to generate high quality multi channel comfort noise.

Abstract: Methods and systems for generating representative data. A generator is configured to create, using a learning model, one or more generated records based on a plurality of training records obtained from a sensitive database. A discriminator is trained to identify the generated records as being generated based on the training records and a privacy adversary is trained to identify a training sample as being more similar to a distribution of the generated records than a distribution of the reference records.

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 created sentence evaluating device 1 using a neural network unit 10 of an encoder/decoder model in which an encoder unit 100 inputs a sentence in a first language, and a decoder unit 101 sequentially outputs word candidates for a sentence in a second language corresponding to the sentence in the first language and likelihood of the word candidates includes: an encoder input unit 13 configured to input a created sentence created in the second language to the encoder unit 100 sequentially for each word; and an evaluation unit 17 configured to evaluate words of the created sentence on the basis of word candidates in the second language and the likelihood of the word candidates output by the decoder unit 101 on the basis of an input from the encoder input unit 13.