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.

Abstract: Implementations relate to mitigating client device latency in rendering of remotely generated automated assistant content. Some of those implementations mitigate client device latency between rendering of multiple instances of output that are each based on content that is responsive to a corresponding automated assistant action of a multiple action request. For example, those implementations can reduce latency between rendering of first output that is based on first content responsive to a first automated assistant action of a multiple action request, and second output that is based on second content responsive to a second automated assistant action of the multiple action request.

Abstract: A computer-implemented method includes receiving user input including codified knowledge management information and/or engine data; and processing the input using one or more trained machine learning models to generate one or more living documents. A computing system includes one or more processors; and a memory having stored thereon instructions that, when executed, cause the computing system to receive user input including codified knowledge management information and/or engine data; and process the user input using one or more trained machine learning models to generate one or more living documents. A non-transitory computer-readable storage medium includes executable instructions that, when executed by a processor, cause a computer to receive user input including codified knowledge management information and/or engine data; and process the user input using one or more trained machine learning models to generate one or more living documents.

Abstract: Techniques are provided for reverberation compensation for far-field speaker recognition. A methodology implementing the techniques according to an embodiment includes receiving an authentication audio signal associated with speech of a user and extracting features from the authentication audio signal. The method also includes scoring results of application of one or more speaker models to the extracted features. Each of the speaker models is trained based on a training audio signal processed by a reverberation simulator to simulate selected far-field environmental effects to be associated with that speaker model. The method further includes selecting one of the speaker models, based on the score, and mapping the selected speaker model to a known speaker identification or label that is associated with the user.

Abstract: In one embodiment, a method includes receiving a user request to automatically debug a natural-language understanding (NLU) model, accessing a plurality of predicted semantic representations generated by the NLU model, wherein the plurality of predicted semantic representations are associated with a plurality of dialog sessions, respectively, wherein each dialog session is between a user and an assistant xbot associated with the NLU model, generating a plurality of expected semantic representations associated with the plurality of dialog sessions based on an auto-correction model, wherein the auto-correction model is learned from dialog training samples generated based on active learning, identifying incorrect semantic representations of the predicted semantic representations based on a comparison between the predicted semantic representations and the expected semantic representations, and automatically correcting the incorrect semantic representations by replacing them with respective expected semantic repre

Abstract: There is a need for more accurate and more efficient natural language solutions with greater semantic intelligence. This need can be addressed, for example, by natural language processing techniques that utilize predictive entity scoring. In one example, a method includes determining an overall prevalence score for the input entity data object with respect to a scored document corpus and a target section; determining a qualified prevalence score for the input entity data object with respect to a high-scoring subset of the scored document corpus; processing the input entity data object using an entity scoring machine learning model to generate the predicted entity score, wherein the entity scoring machine learning model may characterized by a plurality of multiplicative hyper-parameters and one or more additive hyper-parameters; and performing one or more prediction-based actions based at least in part on the predicted entity score.

Abstract: Provided is a method including obtaining a set of ontologies mapping n-grams onto concepts to which the n-grams refer in different respective domains of knowledge. The method includes receiving an update associating a first n-gram with a first concept and receiving information by which the update is associated with a given domain of knowledge. The method includes selecting a subset of ontologies by determining that the update in the given domain of knowledge is applicable to respective domains of knowledge of the subset of ontologies and that the first concept has a specified type of relationship to a subset of concepts to which other n-grams are mapped in the subset of ontologies. The method also includes storing, in response to the determination, associations between the first n-gram and the subset of concepts in at least some of the subset of ontologies in memory of the computer system.

Abstract: A method, electronic device and storage medium for generating information are disclosed. The method includes: acquiring a plurality of tag entity words from a target video, the tag entity words including a person entity word, a work entity word, a video category entity word, and a video core entity word, the video core entity word including an entity word for characterizing a content related to the target video; linking, for a tag entity word among the plurality of tag entity words, the tag entity word to a node of a preset knowledge graph; determining semantic information of the target video based on a linking result of each of the tag entity words; and structuring the semantic information of the target video based on a relationship between the node and an edge of the knowledge graph, to obtain structured semantic information of the target video.

Abstract: A system for identifying industrial ergonomics risk root-causes and providing risk control actions, comprising: a computing device configured to obtain textual information describing a series of tasks of a job and forces being exerted during the series of tasks; and a computing server system configured to receive and process the textual information to generate a set of textual entry to correspond to a unique identifier of the job, identify nouns and verbs in the set of textual entry via natural language processing techniques, perform dependency parsing and part-of-speech tagging to associate each identified verb in the set of textual entry with a root noun in order to identify action-object pairs and unpaired actions, determine ergonomic risk root-causes based at least upon the action-object pairs and the unpaired actions in the set of textual entry, and provide ergonomic risk control recommendations to mitigate the ergonomic risk root-causes.

Abstract: Systems and methods for real-time patient record transcriptions and medical form population via mobile devices are described. A user (e.g., a medical professional) may speak into or near a mobile device operable to detect or record spoken language, and furthermore the mobile device may initiate real-time transcription of the spoken language to generate unstructured transcription text data corresponding to the spoken language. The unstructured transcription text data may be parsed for words or phrases indicative of medical information for generating structured data, where the structured data includes terms, phrases, and values identified via delineators and/or natural language processing techniques. Discrete data from the structured data may be directly inserted into corresponding locations (e.g., appropriate medical form text fields) in electronic medical records via APIs and service bus relays.

Abstract: A computer implemented method for the automated analysis or use of data is implemented by a voice assistant. The method comprises the steps of: (a) storing in a memory a structured, machine-readable representation of data that conforms to a machine-readable language (‘machine representation’); the machine representation including representations of user speech or text input to a human/machine interface; and (b) automatically processing the machine representations to analyse the user speech or text input.

Abstract: Systems, methods, and devices are disclosed for training a model. Media data is separated into one or more clusters, each cluster based on a feature from a first model. The media data of each cluster is sampled and, based on an analysis of the sampled media data, an accuracy of the media data of each cluster is determined. The accuracy is associated with the feature from the first model. Based on a subset dataset of the media data being outside a threshold accuracy, the subset dataset is automatically forwarded to a crowd source service. Verification of the subset dataset is received from the crowd source service, and the verified subset dataset is added to the first model.

Abstract: To increase the accuracy of paralinguistic information estimation. A paralinguistic information estimation model storage unit 20 stores a paralinguistic information estimation model outputting, with a plurality of independent features as inputs, paralinguistic information estimation results. A feature extraction unit 11 extracts the features from an input utterance. A paralinguistic information estimation unit 20 estimates paralinguistic information of the input utterance from the features extracted from the input utterance, by using the paralinguistic information estimation model.

Abstract: Disclosed is a natural language processing technique according to a neural network of high interpretive ability. One embodiment of the present disclosure relates to an apparatus including a trained neural network into which first natural language text is input and that is trained to output second natural language text and alignment information, the second natural language text being in accordance with a predetermined purpose corresponding to the first natural language text, and the alignment information indicating, for each part of the second natural language text, which part of the first natural language text is a basis of information for generation; and an analyzing unit configured to output, upon input text being input into the trained neural network, a predicted result of output text in accordance with a predetermined purpose, and alignment information indicating, for each part of the predicted result of the output text, which part of the input text is a basis of information for generation.

Abstract: Speech analysis is performed by receiving estimated glyphs corresponding to an estimate made by speech-to-text software of what has been spoken out loud by a user; comparing the estimated glyphs with reference glyphs representing a text from which the user has attempted to read; and providing feedback relating to the user's speech based on the comparison of the estimated glyphs with the reference glyphs.

Abstract: A dialysis system, comprising: a dialysis machine; a voice recognition component configured to identify a voice command in audio information received by a microphone of the dialysis system; an authentication component configured to determine a source of the voice command; and a processor configured to perform a function determined based on the voice command.

Abstract: Described herein are improved systems and methods for overcoming technical problems associated with processing and visualization of textual data and natural language processing. In some examples, a method is provided for determining sentiment associated with big data analysis of database information. In some examples, textual news data (e.g., NEWS API, RSS, etc.) is received via a communications network from a plurality of data platforms. The textual news data is parsed, and syntactic dependency trees are generated therefrom. A sentiment score is derived for the parsed textual data corresponding to a word or phrase associated with the textual data, and an image is generated reflecting scored sentiment for the parsed textual data.