Abstract: A language sequence labeling method and includes: reading a first embedding representation of a language sequence, the first embedding representation including a character-level word embedding representation, a pre-trained word embedding representation, and a global word embedding representation of the language sequence, the global word embedding representation referring to a global context representation of the language sequence; performing first depth transformation (DT) encoding on the first embedding representation based on a first DT recurrent neural network (RNN), to output a first hidden-layer state representation corresponding to each word in the language sequence; and decoding the first hidden-layer state representations of the language sequence, to obtain a labeling result of one or more elements in the language sequence.

Abstract: In some embodiments, a method is provided for updating an editing parameter for a model for automatically suggesting revisions to text data. The method may include displaying, on a graphical user interface (GUI) of a user device, one or more interactive input elements, wherein each of the one or more input elements is associated with an editing parameter for a model for automatically suggesting revisions to text data. The method may include receiving, via the GUI, an input from a selected input element of the one or more input elements, wherein the input comprises an indication of a value for a selected editing parameter associated with the selected input element. The method may include updating the selected editing parameter for the model based on the value. The method may include using the model with the updated selected editing parameter to apply an edit operation to an obtained text-under-analysis.

Abstract: A computer assigns a similarity value to a comparison document. The computer receives, reference document contextual word embeddings in first set of topic clusters, each with a representative embedding. The computer receives comparison document contextual word embeddings. The computer determines, using a trained neural network model classifier, for each comparison document contextual word embedding, topic correspondence values relative to the representative embeddings of said first set of clusters. The computer generates a second set of clusters by assigning comparison document embeddings to best matching one of the first clusters, according to the topic correspondence values. The computer determines a second set of representative embeddings and uses a comparison method, to determine a cluster similarity value for second set clusters compared to first set representative embeddings. The computer determines document similarity values based, at least in part, on at least one of cluster similarity values.

Abstract: A primary chatbot may receive a query from a user. The primary chatbot, using natural language processing techniques, may analyze the query. The primary chatbot may identify, from the analyzing, one or more key features of the query. The primary chatbot may push the one or more key features to one or more secondary chatbots. The primary chatbot may identify which one of the primary chatbot and the one or more secondary chatbots is to respond to the query. The primary chatbot may transmit the response to the user.

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: A data processing system receives a plurality of electronic documents in image format. The system extracts text from the electronic documents using an optical character recognition processor, and determines a plurality of entity data based on the extracted text. The system receives pre-defined question data from a user, and determines pre-annotated answer data based on the entity data and the question data using an open-domain question answering model. The system determines context data based on the entity data and the question data. The system provides the pre-annotated answer data to the user, and receives corrected entity data from the user. The system trains a closed-domain question answering model based on the corrected entity data and re-aligned context data. The system determines a plurality of n-gram words based on the corrected entity data and the context data using a context phrase model. The n-grams words are stored in a knowledge base.

Abstract: A computer-implemented method for text conversion, a computer device, and a non-transitory computer readable storage medium are provided. The method includes: obtaining a text to be converted; performing a non-standard word recognition on the text to be converted, to determine whether the text to be converted includes a non-standard word; recognizing the non-standard word in the text to be converted by using an eXtreme Gradient Boosting model in response to the text to be converted including the non-standard word; and obtaining a target converted text corresponding to the text to be converted, according to a recognition result outputted by the eXtreme Gradient Boosting model. The method has a faster recognition speed and a higher recognition accuracy compared with the deep learning model.

Abstract: An electronic apparatus and a controlling method thereof are provided. The method of controlling an electronic apparatus according to an embodiment includes: obtaining first text information including a plurality of words, identifying a security level of the first text information based on at least one of a source from which the first text information is obtained or a type of the first text information, obtaining second text information by converting at least one of the plurality of words included in the first text information based on the identified security level, and obtaining first summary sentence information summarizing the second text information through a summary module.

Abstract: A computer-implemented method is provided for data augmentation. The method includes calculating, by a hardware processor for each of words in a text data, a word replacement probability based on a word occurrence frequency in the text data, wherein the word replacement probability decreases with increasing word occurrence frequency. The method additionally includes selectively replacing at least one of the words in the text data with words predicted therefor by a Bidirectional Neural Network Language Model (BiNNLM) to generate augmented text data, based on the word replacement probability.

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: 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: An Industrial Virtual Assistant (IVA) platform with Robotic Process Automation that operates like a Digital Knowledge Companion and allows operational staff at industrial facilities to have natural language conversations with the IVA to obtain information about, and to control operations of, industrial facilities, and which automates certain processes based in part on those natural language conversations. In an embodiment, the platform uses a Robotic Process Automater (RPA) to ingest information from documentation, human inputs, and operational data from the facility, organize that information into a knowledge graph containing comprehensive facility information, and apply machine learning algorithms to the knowledge graph to provide natural language responses to human queries and to automate certain processes of the facility.

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: Systems and methods for sentence fusion are described. Embodiments receive coreference information for a first sentence and a second sentence, wherein the coreference information identifies entities associated with both a term of the first sentence and a term of the second sentence, apply an entity constraint to an attention head of a sentence fusion network, wherein the entity constraint limits attention weights of the attention head to terms that correspond to a same entity of the coreference information, and predict a fused sentence using the sentence fusion network based on the entity constraint, wherein the fused sentence combines information from the first sentence and the second sentence.

Abstract: A computerized method for reducing domain noise, creating and summarizing human-written sentences into clusters for efficient tagging in natural language processing comprising: receiving a typed, handwritten or printed text; implementing an optical character recognition (OCR) process on human written text to generate a digital version of the human written text; splitting the digital version of the typed, handwritten or printed text into an array of sentences, using a sentence splitter to generate a split sentence version; determining a domain of the human written text; based on the domain, implementing a domain noise reduction process on the split sentences version; hierarchically clustering the split sentences version after the domain noise reduction process; and summarizing the clustered sentences and reducing the amount of data to be tagged.

Abstract: An encoder for encoding a parametric spectral representation (f) of auto-regressive coefficients that partially represent an audio signal. The encoder includes a low-frequency encoder configured to quantize elements of a part of the parametric spectral representation that correspond to a low-frequency part of the audio signal. It also includes a high-frequency encoder configured to encode a high-frequency part (fH) of the parametric spectral representation (f) by weighted averaging based on the quantized elements ({circumflex over (f)}L) flipped around a quantized mirroring frequency ({circumflex over (f)}m), which separates the low-frequency part from the high-frequency part, and a frequency grid determined from a frequency grid codebook in a closed-loop search procedure. Described are also a corresponding decoder, corresponding encoding/decoding methods and UEs including such an encoder/decoder.

Abstract: A system for generating textual instructions for manufacturers from hybrid textual and image data includes a manufacturing instruction generator that may generate a language processing module from a first training set including at least a training annotated file describing at least a first product to manufacture, the at least an annotated file containing one or more textual data, and at least an instruction set containing one or more manufacturing instructions to manufacture the at least a first product. Manufacturing instruction generator may use the language processing to generate textual instructions for manufacturers from at least an annotated file and may initiate manufacture using the generated manufacturing instructions.

Abstract: A natural language model can be primed utilizing optimized examples generated from a labeled knowledge graph corresponding to an independently developed application program. Parsing of the labeled knowledge graph can include the identification of triples, comprising a source node, a destination node, and a link between them, each of which can be labeled. One or more natural language input examples can be generated from an individual triple by concatenating the natural language words or phrases utilized to label the source node in the link. Determinations that subsequently received natural language user input is similar to the generated examples can result in an identification of the triple, which can, in turn, trigger the performance of a function associated with the destination node of the triple. Labels can include preferred labels and alternative labels, and various permutations thereof can be concatenated to generate alternative natural language input examples.

Abstract: System and methods of creating and using a transparent, computable contractual natural language are disclosed in which a set of legal contracts are text mined to obtain a structured contractual database. A set of categorized contractual phrases are assembled from the structured contractual database. A transparent knowledge representation language is defined having a set of syntax rules, a set of semantic rules and a set of inference rules. A transparent, computable contractual natural language is the set of contractual phrases that map to the transparent knowledge representation language. A user writes computable legal documents comprised of phrases contained in the transparent, computable contractual natural language.

Abstract: Systems, methods, and apparatuses for contextual natural language understanding are detailed. An exemplary method includes receiving a user utterance provided by a user within a multi-turn chat dialog between the user and a conversational agent; providing to a contextual natural language understanding framework: the user utterance, and contextual information associated with one or more previous turns of the multi-turn chat dialog, the contextual information associated with each turn of the one or more previous turns including a previous intent, a previous dialog act, and an elicited slot; and obtaining, from the contextual natural language understanding framework, an intent classification and one or more slot labels.