Abstract: An online system allows user interactions using natural language expressions. The online system uses a machine learning based model to infer an intent represented by a user expression. The machine learning based model takes as input a user expression and an example expression to compute a score indicating whether the user expression matches the example expression. Based on the scores, the intent inference module determines a most applicable intent for the expression. The online system determines a confidence threshold such that user expressions indicating a high confidence are assigned the most applicable intent and user expressions indicating a low confidence are assigned an out-of-scope intent. The online system encodes the example expressions using the machine learning based model. The online system may compare an encoded user expression with encoded example expressions to identify a subset of example expressions used to determine the most applicable intent.

Abstract: Systems and methods for anonymizing content suggestive of a particular characteristic while preserving relevant content are disclosed.

Abstract: To arrange all words so that the distance of a given word pair will be appropriate. Using as input a concept base 22 which is a set of pairs of a word and a vector representing a concept of the word, and a dictionary 24 which is a set of semantically distant or close word pairs, when a word pair C being a pair of given words A, B in the concept base 22 is present in the dictionary 24, conversion means 30 associates with the word pair C a magnitude D of a difference vector between a difference vector V? between a converted vector of the word A and a converted vector of the word B, and a vector kV determined by multiplying a difference vector V between the vector of the word A in the concept base 22 and the vector of the word B in the concept base 22 by a scalar value k. When the word pair C is not present in the dictionary 24, the conversion means 30 associates the magnitude D of the difference vector between the difference vector V? and the difference vector V with the word pair C.

Abstract: Computer-implemented methods for speech synthesis are provided. A speech synthesizer may be trained to generate synthesized audio data that corresponds to words uttered by a source speaker according to speech characteristics of a target speaker. The speech synthesizer may be trained by time-stamped phoneme sequences, pitch contour data and speaker identification data. The speech synthesizer may include a voice modeling neural network and a conditioning neural network.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for modulating language model biasing. In some implementations, context data is received. A likely context associated with a user is determined based on at least a portion of the context data. One or more language model biasing parameters based at least on the likely context associated with the user is selected. A context confidence score associated with the likely context based on at least a portion of the context data is determined. One or more language model teasing parameters based at least on the context confidence score is adjusted. A baseline language model based at least on the one or more of the adjusted language model biasing parameters is biased. The baseline language model is provided for use by an automated speech recognizer (ASR).

Abstract: A knowledge base is collaboratively developed by receiving language input from at least one editor, featurizing it into language elements, extracting predicate sets that are missing predicate arguments, querying editors for input regarding the missing arguments, and updating the knowledge base with suitable predicate arguments and other language elements provided by the editors.

Abstract: A likelihood of voice that is a discrimination measure between noise and voice is corrected, by using a Gaussian mixture model of noise learned in a time section in which an input signal is noise, and a voice activity is detected on the basis of the corrected likelihood of voice.

Abstract: Systems and method herein describe embedding graphs into a semantic multidimensional space by receiving a dataset, constructing a Markov chain from the dataset, the Markov chain comprising a plurality of nodes selecting a basis node and a target node from the plurality of nodes, determining a distance from the target node to the basis node, storing the distance between the target node and the basis node in a vector, analyzing the vector, and determining a semantic characteristic of the target node based on the analysis of the vector.

Abstract: A semantic vector generation device (100) obtains vectors of a plurality of words included in text data. The semantic vector generation device (100) extracts a word included in any group. The semantic vector generation device (100) generates a vector in accordance with the any group on the basis of a vector of the word extracted among the obtained vectors of the words. The semantic vector generation device (100) identifies a vector of a word included in an explanation of any semantics of the word extracted among the obtained vectors of the words. The semantic vector generation device (100) generates a vector in accordance with the any semantics on the basis of the vector identified and the vector generated.

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: Techniques for evaluating a natural language understanding (NLU) component and determining an action to resolve an issue processing a user input are described. The system determines which component is invoked by a baseline NLU component is processing the user input, and which component is invoked by an updated NLU component. Based on that information, the system selects the action to resolve the updated NLU component generating an undesired response to the user input.

Abstract: A speech recognition method includes adding a preset special sequence to a front end of an input sequence that corresponds to an input utterance of a speaker, recognizing the preset special sequence and the input sequence, and recognizing the input sequence based on the preset special sequence and a speech recognition result obtained by recognizing the preset special sequence and the input sequence.

Abstract: A method processes natural language commands (e.g., for data visualization). The method includes obtaining word embeddings (e.g., word vectors) for a set of words (or phrases) of a natural language. In some implementations, the set of words includes high-frequency or common words of the natural language. The method also includes training a word similarity model to identify similar words based on the word embeddings and a synonym database (a large lexical database, such as a thesaurus). The method also includes generating semantic annotations for a published data source using the trained word similarity model, based on the synonym database, and the word embeddings. The method also includes generating a semantic interpretation for a natural language command based on the semantic annotations for the published data source. The method also includes querying the published data source based on the sematic interpretation, thereby retrieving a dataset.

Abstract: A naming support system is provided that includes a processing unit that receives first language name information input from a user, determines name evaluation's basic information about the first language name information, and generates and transmits name's evaluation information to an output unit based on a target language which includes at least one of a plurality of languages for the name evaluation's basic information, wherein the first language name information includes at least one of character notation information of a first language name, pronunciation information of a first language name, or desired information for a first language name, and the name evaluation's basic information includes the first language name information.

Abstract: A method for applying semantic information to data in a building management system (BMS). The method includes receiving unrecognized data from equipment associated with the BMS, the unrecognized data comprising a first value and an associated device identifier; providing the unrecognized data as input to a first learning model to generate a first output, the first output indicative of semantic information corresponding to the first value evaluated individually; providing the unrecognized data as input to a second learning model to generate a second output, the second output indicative of semantic information corresponding to the first value evaluated in context of a second value associated with the device identifier; and applying semantic information to the unrecognized data based on the first output and the second output. The method allows for users to configure building management systems with automatically generated semantic data tags.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for selecting a text span from an input electronic document that answers an input question. One of the methods includes obtaining a respective first numeric representations of text spans in the input document; for each of the text spans: determining, for a segment that contains the text span, a question-aware segment vector, determining, for the question, a segment-aware question vector, and processing the first numeric representation of the text span, the question-aware segment vector, and the segment-aware question vector using a second feedforward neural network to generate a second numeric representation of the text span; for each unique text span in the plurality of text spans: determining an aggregate representation for the unique text span, and determining, from the aggregate representation, a final score for the unique text span; and selecting a unique text span.

Abstract: A method includes receiving user inputs; receiving codified knowledge management information; receiving engine data; and processing the user inputs, the codified knowledge management information and engine data using a trained machine learning model to generate a living document. A computing system includes one or more processors; and a memory comprising instructions that, when executed, cause the computing system to: receive user inputs; receive codified knowledge management information; receive engine data; and process the user inputs, the codified knowledge management information and engine data using a trained machine learning model to generate a living document.

Abstract: The present disclosure relates to a corpus processing method, a corpus processing apparatus and a storage medium. The corpus processing method can include obtaining a message input by a user, retrieving a reply message matching the message input by the user from a plurality of candidate corpora, in which the plurality of the candidate corpora includes candidate corpora obtained after removing a negative emotion corpus, and sending the reply message.

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: Disclosed herein is a system and method for Natural Language Processing (NLP) of real world documents. the system and method combines various models not previously combined and overcomes the challenges of this combination. Models include an encoder-decoder model, a spatial model, and a multi-modal model. An iterative training process receives documents and generates outputs, wherein the iterative training process comprises enabling information retrieval from documents without training data.