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: Disclosed is a method and an apparatus NER-orientated Chinese clinical text data augmentation, and unannotated data and annotated data of label linearization processing through data preprocessing. A concealed part is predicted based on retained information by using the unannotated data and concealing part of information in text, and meanwhile an entity word-level discrimination task is introduced for pre-training of a span-based language model; and a plurality of decoding mechanisms are introduced in a fine-tune stage, a relationship between a text vector and text data is obtained based on the pre-trained span-based language model, linearized data with entity labels is converted into the text vector, and text generation is performed through forward decoding and reverse decoding in a prediction stage of a text generation model to obtain enhanced data with annotation information.

Abstract: Disclosed is a voice recognition method based on a neural network, performed by one or more processors of a computing device. The voice recognition method includes generating first text data based on a first language based on voice information. The method includes detecting problem text among the generated first text data. The method includes detecting a second language corresponding to the detected problem text. The method includes generating second text data based on the detected second language, in which the second language is different from the first language.

Abstract: Techniques for performing speech processing using multi-modal widget information are described. A system may receive input data corresponding to a user input. The system may also receive widget context data corresponding to one or more multi-modal widgets active at a device. The system may use the widget context data to perform natural language understanding (NLU) processing with respect to the user input, and for selecting a skill component for responding to the user input. The system may send a widget identifier to the skill component when invoking the skill to respond to the user input.

Abstract: The techniques described herein relate to techniques for verifying a veracity of machine learning outputs. An example method includes receiving a first output generated by a first model responsive to a first input, the first output comprising one or more verifiable statements in text, verifying, using a second model and first reference data stored in at least one first datastore, the one or more verifiable statements to produce first verification results indicating which of them has been verified, when it is determined that at least one of them remains unverified based on the first verification results, identifying, using at least one of the first or second models, at least one second datastore having second reference data attesting to veracity of the first output; and verifying, using the second model and the second reference data, the at least one unverified statement to produce second verification results to be provided as output.

Abstract: A method includes performing, using at least one processor, feature extraction of input audio data to identify extracted features associated with the input audio data. The method also includes detecting, using the at least one processor, a language associated with the input audio data by processing the extracted features using a plurality of language models, where each language model is associated with a different language. The method further includes directing, using the at least one processor, the input audio data to one of a plurality of automatic speech recognition (ASR) models based on the language associated with the input audio data.

Abstract: A voice controlled device comprises a housing, a dock, a coupling mechanism, and a microphone. The dock is configured to connect the housing to a plurality of host appliances. The coupling mechanism is configured to receive an identification value indicative of docking between the voice controlled device and a currently connected host appliance of the plurality of host appliances. The microphone is configured to receive one or more voice inputs for the currently connected host appliance. A command is provided based on the one or more voice inputs and the identification value.

Abstract: A method of processing a video file to generate a modified video file, the modified video file including a translated audio content of the video file, the method comprising: receiving the video file; accessing a facial model or a speech model for a specific speaker, wherein the facial model maps speech to facial expressions, and the speech model maps text to speech; receiving a reference content for the originating video file for the specific speaker; generating modified audio content for the specific speaker and/or modified facial expression for the specific speaker; and modifying the video file in accordance with the modified content and/or the modified expression to generate the modified video file.

Abstract: The technology described in this document can be embodied in a computer-implemented method that includes receiving, at a processing system, a first signal including an output of a speaker device and an additional audio signal. The method also includes determining, by the processing system, based at least in part on a model trained to identify the output of the speaker device, that the additional audio signal corresponds to an utterance of a user. The method further includes initiating a reduction in an audio output level of the speaker device based on determining that the additional audio signal corresponds to the utterance of the user.

Abstract: Methods, systems, and computer programs are presented for providing access to a cloud data platform including a machine learning model for performing a plurality of iterations, by at least one hardware processor, to generate a Natural Language Processing (NLP) model. The cloud data platform performs each iteration by receiving real-world documents and enabling information retrieval from the real-world documents without annotated training data. Each iteration includes receiving data comprising text data, layout data, and image data and analyzing the text data, the layout data, and the image data. The cloud data platform generates one or more outputs from the machine learning model by applying the iterative training on new data, based at least in part on the analyzing of the text data, the layout data, and the image data.

Abstract: Systems, methods and non-transitory computer readable media for identifying prompts used for training of inference models are provided. In some examples, a specific textual prompt in a natural language may be received. Further, data based on at least one parameter of an inference model may be accessed. The inference 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. The data and the specific textual prompt may be analyzed to determine a likelihood that the specific textual prompt is included in at least one training example of the plurality of training examples. A digital signal indicative of the likelihood that the specific textual prompt is included in at least one training example of the plurality of training examples may be generated.

Abstract: A method for selecting a speech recognition result on a computing device includes receiving a first speech recognition result determined by the computing device, receiving first features, at least some of the features being determined using the first speech recognition result, determining whether to select the first speech recognition result or to wait for a second speech recognition result determined by a cloud computing service based at least in part on the first speech recognition result and the first features.

Abstract: Methods, apparatus, and computer readable media related to receiving textual input of a user during a dialog between the user and an automated assistant (and optionally one or more additional users), and generating responsive reply content based on the textual input and based on user state information. The reply content is provided for inclusion in the dialog. In some implementations, the reply content is provided as a reply, by the automated assistant, to the user's textual input and may optionally be automatically incorporated in the dialog between the user and the automated assistant. In some implementations, the reply content is suggested by the automated assistant for inclusion in the dialog and is only included in the dialog in response to further user interface input.

Abstract: Methods and systems are presented for analyzing feedback data associated with a content and generating an interactive graphical representation of the feedback data. Upon receiving a request from a user, a feedback analysis system may access feedback data associated with a content from a content hosting server. The feedback data may include comments submitted by viewers of the content. The feedback analysis system may analyze the comments and generate an interactive graphical representation of the feedback data. The interactive graphical representation may include icons that represents keywords that are relevant to the comments and sentiments of the viewers derived based on the comments. Upon receiving a selection of an icon, the feedback analysis system may present a comment that corresponds to the keyword and/or sentiment represented by the icon.

Abstract: A quantization device includes: a trellis-structured vector quantizer which quantizes a first error vector between an N-dimensional (here, “N” is two or more) subvector and a first predictive vector; and an inter-frame predictor which generates a first predictive vector from the quantized N-dimensional subvector, wherein the inter-frame predictor uses a predictive coefficient comprising an N×N matrix and performs an inter-frame prediction using the quantized N-dimensional subvector of a previous stage.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for handing off a user conversation between computer-implemented agents. One of the methods includes receiving, by a computer-implemented agent specific to a user device, a digital representation of speech encoding an utterance, determining, by the computer-implemented agent, that the utterance specifies a requirement to establish a communication with another computer-implemented agent, and establishing, by the computer-implemented agent, a communication between the other computer-implemented agent and the user device.

Abstract: A computer-implemented process includes obtaining a natural-language-text document comprising a first and second clause and determining first and second embedding sequences based on n-grams of the first and second clauses. The process includes generating data model objects based on the embedding sequences and determining an association between the first data model object and the second data model object based on a shared parameter of the first and second clauses. The process includes receiving a query including the first category and the first n-gram and causing a presentation of a visualization of data model objects that includes shapes based on the data model objects and a third shape based on the association between the first data model object and the second data model object.

Abstract: Disclosed herein are methods, systems, and computer-readable media for automatically generating and inserting text. In an embodiment, a method may include receiving an input text prompt comprising a prefix portion and a suffix portion. The method may also include accessing a language model based on the input text prompt, and determining a set of context parameters based on the input text prompt and the language model. The method may also include generating an output text prompt based on the set of context parameters and the language model, and inserting the output text prompt into the input text prompt.

Abstract: Methods and systems for hierarchical natural language understanding are described. A representation of an utterance is inputted to a first machine learning model to obtain information on the first utterance. According to the information on the utterance a determination that the representation of the utterance is to be inputted to a second machine learning model that performs a dedicated natural language task is performed. In response to determining that the representation of the utterance is to be inputted to a second machine learning model, the utterance is inputted to the second machine learning model to obtain an output of the dedicated natural language task.

Abstract: Techniques are disclosed for assisting users with unknown topics by automatically presenting information associated with the unknown topics to the users. In an example embodiment, an unknown topic is referred to or discussed during a conversation between multiple users. A candidate definition for the topic is determined, where the candidate definition is known by the user that used the topic. Based on a determination that the topic and the candidate definition are unknown to a second user in the conversation, the topic and the candidate definition are provided to one or more output devices for presentation to the second user.