Abstract: A method for neural network training is provided. The method inputs a training set of textual claims, lists of evidence including gold evidence chains, and claim labels labelling the evidence with respect to the textual claims. The claim labels include refutes, supports, and not enough information (NEI). The method computes an initial set of document retrievals for each of the textual claims. The method also includes computing an initial set of page element retrievals including sentence retrievals from the initial set of document retrievals for each of the textual claims. The method creates, from the training set of textual claims, a Leave Out Training Set which includes input texts and target texts relating to the labels. The method trains a sequence-to-sequence neural network to generate new target texts from new input texts using the Leave Out Training Set.

Abstract: Text editing apparatus comprises a database memory configured to store a text database, in which the text database is configured to store a plurality of text portions and a set of links between text portions, the set of links defining a document as a linked list of the text portions; and a data processor configured, in response to user input, to perform an editing operation to edit the text database so as to define an edited document by changing at least one of: (i) text within a text portion and (ii) the set of links between text portions.

Abstract: A system, method and computer product for training a neural network system. The method comprises applying an audio signal to the neural network system, the audio signal including a vocal component and a non-vocal component. The method also comprises comparing an output of the neural network system to a target signal, and adjusting at least one parameter of the neural network system to reduce a result of the comparing, for training the neural network system to estimate one of the vocal component and the non-vocal component. In one example embodiment, the system comprises a U-Net architecture. After training, the system can estimate vocal or instrumental components of an audio signal, depending on which type of component the system is trained to estimate.

Abstract: In certain embodiments, speech is converted to text for theme identification by natural language processing. Notification data is generated based on detected themes and the notification data may include rules for notification presentation on a client device. The notification data may include parameters for processing image data captured by an augmented reality device to detect one or more objects. The objects may be associated with the theme and detection thereof within captured image data, and in accordance with other rules, may cause the augmented reality device to present a notification with contextual relevance to a current environment of a user utilizing the augmented reality device.

Abstract: A system, method and computer product for training a neural network system. The method comprises inputting an audio signal to the system to generate plural outputs f(X, ?). The audio signal includes one or more of vocal content and/or musical instrument content, and each output f(X, ?) corresponds to a respective one of the different content types. The method also comprises comparing individual outputs f(X, ?) of the neural network system to corresponding target signals. For each compared output f(X, ?), at least one parameter of the system is adjusted to reduce a result of the comparing performed for the output f(X, ?), to train the system to estimate the different content types. In one example embodiment, the system comprises a U-Net architecture. After training, the system can estimate various different types of vocal and/or instrument components of an audio signal, depending on which type of component(s) the system is trained to estimate.

Abstract: In accordance with one embodiment, a system includes a processor, a memory module communicatively coupled to the processor, an NLP module communicatively coupled to the processor, and a set of machine-readable instructions stored in the memory module. The machine-readable instructions, when executed by the processor, direct the processor to perform operations including receiving a text data, and receiving a training text data for training one or more models of the NLP module. The operations also include generating, with a novice model of the NLP module, a novice suggestion based on the text data and the training text data to present an idea related to the text data, generating, with an expert model of the NLP module, an expert suggestion based on the text data and the training text data to present an idea elaborating on the text data, and outputting the novice suggestion and/or the expert suggestion.

Abstract: Methods for generating a categorized, ranked, condensed summary of a transcript of a conversation, involving obtaining a diarized version of the transcript of the conversation, storing textual monologues from the transcript, determining classifications as to the textual monologues based on a classifier algorithm, associating the classifications with the textual monologues, creating textually-modified rephrasings of the textual monologues based on text and classification thereof, storing the textually-modified rephrasings, aggregating the textually-modified rephrasings based on associated clustering and scoring, and transmitting summary information pertaining to the aggregated textually-modified rephrasings to a user device.

Abstract: A remote control for generating output signals apt at controlling one or more electronic devices includes a sound transducer, a speech recognition unit for recognizing voice commands, a memory for storing information relative to available content of the one or more electronic devices and a control signal generating and receiving unit for generating control signals corresponding to the voice commands for controlling the one or more electronic devices.

Abstract: An acoustic crosstalk suppression device includes a speaker estimation unit configured to estimate a main speaker based on voice signals collected by n units of microphones corresponding to n number of persons (n: an integer equal to or larger than 3); n units of filter update units each of which is configured to update a parameter of a filter configured to generate a suppression signal of a crosstalk component included in a voice signal of the main speaker; and a crosstalk suppression unit configured to suppress the crosstalk component by using a synthesis suppression signal generated by the maximum (n-1) units of filter update units corresponding to reference signals collected by the maximum (n-1) units of microphones.

Abstract: The present disclosure may provide a voice audio data processing system. The voice audio data processing system may obtain voice audio data, which includes one or more voices, each being respectively associated with one of one or more subjects. For one of the one or more voices and the subject associated with the voice, the voice audio processing system may generate a text based on the voice audio data. The text may have one or more sizes, each size corresponding to one of one or more volumes of the voice. The text may have one or more colors, each color corresponding to one of one or more emotion types of the voice.

Abstract: A command analysis device capable of shortening the time until a command is executed is provided. The command analysis device includes a speech recognition unit that performs, every time when a predetermined unit of a speech signal is input, speech recognition on the speech signal and acquires a partial speech recognition result which is an intermediate result, and a command analysis unit that verifies an intermediate result in light of a predetermined intermediate result recognition rule, and outputs an analysis result during the input of the speech signal when a command execution target and a command execution content are successfully analyzed are provided.

Abstract: There is a need for more effective and efficient text categorization. This need can be addressed by, for example, techniques for semantic text categorization. In one example, a method includes determining an input vector-based representation of an input document; processing the input vector-based representation using a trained supervised machine learning model to generate the categorization based at least in part on the input vector-based representation, wherein: (i) the trained supervised machine learning model has been trained using automatically-generated training data, and (ii) the automatically generated training data is generated by determining an inferred semantic label for each unlabeled training document of one or more unlabeled training documents; and performing one or more categorization-based actions based at least in part on the categorization, and (iii) the labels are described by one or more short documents/short texts.

Abstract: Embodiments of this disclosure disclose a sentence processing method and device. The method may include performing word segmentation operation on a source sentence to be encoded to obtain m words. The method may further include obtaining an ith word in the m words using an ith encoding processing node in the n encoding processing nodes, and obtaining an (i?1)th word vector from an (i?1)th encoding processing node. The method may further include performing linear operation and non-linear operation on the ith word and the (i?1)th word vector using the first unit of the ith encoding processing node to obtain an ith operation result, and outputting the ith operation result to the at least one second unit for processing to obtain an ith word vector. The method may further include generating, in response to obtaining m word vectors, a sentence vector according to the m word vectors.

Abstract: Systems, devices, and methods discussed herein provide improved autonomous agent applications that are configured to generate automated answers to a question using summarized logical forms (SLFs). A myriad of techniques may be utilized to generate one or more summarized logical forms for an answer, where the summarized logical form(s) identifies the main entities/informative portions of the answer. Instead of indexing the whole of the answer as in conventional methods, an answer can be indexed using the summarized logical forms. A subsequent query may be converted to logical form to generate a query representation which can be compared to one or more SLFs of a set of answers. If an SLF of an answer matches the query representation, the answer may be provided in response to the question. By indexing the answer with its informative portions, the speed and accuracy of identifying the answer is improved.

Abstract: An apparatus for the generation of a collaboration score is disclosed. The apparatus includes at least a processor and a memory communicatively connected to the at least a processor. The memory instructs the processor to receive a plurality of entity profiles from a plurality of entities, wherein each of the plurality of entity profiles includes entity data. The memory instructs the processor to identify a plurality of opportunity data as a function of the plurality of entity profiles. The memory instructs the processor to generate collaboration data as a function of the plurality of opportunity data. The memory instructs the processor to determine a collaboration score as a function of the collaboration data. The memory instructs the processor to draft a collaboration report as a function of the collaboration score and the collaboration data. The memory instructs the processor to display the collaboration report using a display device.

Abstract: In an embodiment of a messaging system, a method for presenting a commercial message to a user is provided. A target language in which the user is comfortable communicating may be determined based on at least one communication received by the user or at least one communication provided by the user. The commercial message may be presented to the user in the target language.

Abstract: A coding method and a decoding method are provided which can use in combination a predictive coding and decoding method which is a coding and decoding method that can accurately express coefficients which are convertible into linear prediction coefficients with a small code amount and a coding and decoding method that can obtain correctly, by decoding, coefficients which are convertible into linear prediction coefficients of the present frame if a linear prediction coefficient code of the present frame is correctly input to a decoding device.

Abstract: A recognition method and device of named entity, a creation method of dictionary of named entity, an electronic device, and a computer-readable medium. The method includes: obtaining target text; determining to-be-classified word and part-of-speech classification thereof in the target text according to CRF model, the CRF model including semantic function and template function; each template function being configured to provide a score for each character corresponding to each part-of-speech classification in the target text; the semantic function being configured to match at least part of word in the target text with a sememe in sememe library, and give a score of part-of-speech classification corresponding to a type attribute of the sememe in the sememe library for each character of the word when the word has a matched sememe; and determining the named entity in the target text according to the part-of-speech classification of the to-be-classified word.

Abstract: A system for informing cooking style decisions, the system including a computing device designed and configured to receive a personal recipe relating to a user. The computing device also designed and configured to select a cooking style, including locating in a recipe database a set of cooking styles associated with the personal recipe and selecting the cooking style from the set of cooking styles as a function of the user's biological extraction. Additionally, the computing device is designed and configured to incorporate the cooking style into the personal recipe of the user.

Abstract: A computing system receives an instruction to initiate audio presentation of electronic communications for a recipient, and outputs an audio presentation responsive to the instruction. The audio presentation includes an initial portion that includes a presentation road map, and a subsequent portion that includes audible output of text content of a plurality of unreviewed electronic communications for the recipient. The presentation road map identifies an estimated duration of time to present the subsequent portion of the audio presentation.