Abstract: A tool for managing text-item recognition systems such as NER (Named Entity Recognition) systems. The tool applies the system to a text corpus containing instances of text items, such as named entities, to be recognized by the system, and selecting from the text corpus a set of instances of text items which the system recognized. The tool tokenizes the text corpus such that each instance in the aforementioned set is encoded as a single token and processing the tokenized text via a word embedding scheme to generate a word embedding matrix. The tool, responsive to selecting a seed token corresponding to an instance in the aforementioned set, performs a nearest-neighbor search of the embedding space to identify a set of neighboring tokens for the seed token, and identifies the text corresponding to each neighboring token as a potential instance of a text item to be annotated.

Abstract: Systems, methods, and computer-executable instructions for identifying a candidate include receiving unscripted communication, the unscripted communication comprising communication from a first speaker. Properties of the unscripted communication are extracted. A psychographic classifier classifies the first speaker into a psychographic category based on the extracted properties. An aggregate psychographic category of a team is determined based on psychographic categories of each of the team members of the team. A weakness in the aggregate psychographic category of the team is determined. A new team member that has a psychographic category that addresses the weakness in the aggregate psychographic category of the team is identified. A recommendation that the first speaker become a team member of the team is provided.

Abstract: Methods and systems for artificial intelligence (AI)-assisted document annotation and training of machine learning-based models for document data extraction are described. The methods and systems described herein take advantage of a continuous machine learning approach to create document processing pipelines that provide accurate and efficient data extraction from documents that include structured text, semi-structured text, unstructured text, or any combination thereof.

Abstract: Embodiments described herein provide for automatically classifying the types of devices that place calls to a call center. A call center system can detect whether an incoming call originated from voice assistant device using trained classification models received from a call analysis service. Embodiments described herein provide for methods and systems in which a computer executes machine learning algorithms that programmatically train (or otherwise generate) global or tailored classification models based on the various types of features of an audio signal and call data. A classification model is deployed to one or more call centers, where the model is used by call center computers executing classification processes for determining whether incoming telephone calls originated from a voice assistant device, such as Amazon Alexa® and Google Home®, or another type of device (e.g., cellular/mobile phone, landline phone, VoIP).

Abstract: Embodiments of the present invention provide systems, methods, and non-transitory computer storage media for parsing a given input referring expression into a parse structure and generating a semantic computation graph to identify semantic relationships among and between objects. At a high level, when embodiments of the preset invention receive a referring expression, a parse tree is created and mapped into a hierarchical subject, predicate, object graph structure that labeled noun objects in the referring expression, the attributes of the labeled noun objects, and predicate relationships (e.g., verb actions or spatial propositions) between the labeled objects. Embodiments of the present invention then transform the subject, predicate, object graph structure into a semantic computation graph that may be recursively traversed and interpreted to determine how noun objects, their attributes and modifiers, and interrelationships are provided to downstream image editing, searching, or caption indexing tasks.

Abstract: A natural language processing method includes obtaining a to-be-processed phrase, where the to-be-processed phrase includes M words, determining polarity characteristic information of m to-be-processed words in the M words, where polarity characteristic information of an ith word in the m to-be-processed words includes n polarity characteristic values, and each polarity characteristic value corresponds to one sentiment polarity, determining a polarity characteristic vector of the to-be-processed phrase based on the polarity characteristic information of the m to-be-processed words, where the polarity characteristic vector includes n groups of components in a one-to-one correspondence with n sentiment polarities, and determining a sentiment polarity of the to-be-processed phrase based on the polarity characteristic vector of the to-be-processed phrase using a preset classifier, and outputting the sentiment polarity.

Abstract: Text may be modified according to a specified attribute value, such as changing a 1-star review to a 5-star review. To modify the text, an input sequence of tokens may be obtained corresponding to the text. Mask scores may be computed for the tokens by processing the input sequence of tokens with masking neural network. One or more tokens may be selected using the mask scores, and a masked sequence of tokens may be generated by replacing the selected tokens with a mask token. The masked sequence of tokens may be processed by a language model neural network to select a replacement token for each of the mask tokens. Modified text may then be generated using the selected replacement tokens. The modified text may be used for any appropriate application, such as suggesting messages to users participating in a conversation.

Abstract: Techniques are disclosed for improved autonomous agents that can provide a recommendation in a non-intrusive, conversational manner. In an aspect, a method determines a first sentiment score for a first utterance and a second sentiment score for a second utterance, each sentiment score indicating an emotion indicated by the respective utterance. The method further identifies that a difference between the first sentiment score and the second sentiment score is greater than a threshold. The method further extracts a noun phrase from the second utterance. The method identifies a text fragment that includes an entity that corresponds to the noun phrase. The method identifies that the text fragment addresses a claim of the second utterance. The method forms a third utterance that includes the a recommendation related to the second utterance and adds the third utterance to the sequence of utterances after the second utterance.

Abstract: System and method for relation extraction using adaptive thresholding and localized context pooling (ATLOP). The system includes a computing device, the computing device has a processer and a storage device storing computer executable code. The computer executable code is configured to provide a document; embed entities in the document into embedding vectors; and predict relations between a pair of entities in the document using their embedding vectors. The relation prediction is performed based on an improved language model. Each relation has an adaptive threshold, and the relation between the pair of entities is determined to exist when a logit of the relation between the pair of entities is greater than a logit function of the corresponding adaptive threshold.

Abstract: A method is provided that includes obtaining two or more microphone audio signals; analysing the two or more microphone audio signals for a defined noise type; and processing the two or more microphone audio signals based on the analysis to generate at least one audio signal suitable for automatic speech recognition. A corresponding apparatus is also provided.

Abstract: A method for generalized structured data discovery may include (1) receiving physical application metadata from data sources for an attribute, a database object, or a database; (2) receiving reference data comprising a plurality of tokens and their associated abbreviations/acronyms; (3) parsing the physical application metadata into a application tokens comprising known and unknown application tokens; (4) identifying unknown application tokens by comparing the parsed application tokens to a corpus; (5) performing probabilistic parsing on the unknown application tokens using the reference data; (6) performing bi-directional encoding to expand the polysemous tokens to relevant expressions using the reference data; (7) applying language tokens to the relevant expressions in the expanded polysemous tokens to disambiguate the relevant expressions; and (8) outputting a mapping of the physical application metadata to enhanced physical application metadata, wherein the enhanced physical application metadata comprises

Abstract: A computer system includes memory storing computer-executable instructions and a processor configured to execute the computer-executable instructions. The computer-executable instructions include building a questions table including multiple first questions and multiple potential requirements to which the first questions correspond, respectively. The computer-executable instructions include adding, to the questions table, one or more second questions, each of which correspond to at least two requirements from among the potential requirements. The computer-executable instructions include adding, to the questions table, for each second question among the one or more second questions, the at least two requirements to which the second question corresponds. The computer-executable instructions include determining a question, from among the first questions and the second questions, that corresponds to a highest number of potential requirements, and displaying the determined question to a user.

Abstract: Presented herein are embodiments of state-of-the-art speech recognition systems developed using end-to-end deep learning. In embodiments, the model architecture is significantly simpler than traditional speech systems, which rely on laboriously engineered processing pipelines; these traditional systems also tend to perform poorly when used in noisy environments. In contrast, embodiments of the system do not need hand-designed components to model background noise, reverberation, or speaker variation, but instead directly learn a function that is robust to such effects. Neither a phoneme dictionary, nor even the concept of a “phoneme,” is needed. Embodiments include a well-optimized recurrent neural network (RNN) training system that can use multiple GPUs, as well as a set of novel data synthesis techniques that allows for a large amount of varied data for training to be efficiently obtained.

Abstract: An electronic device and a method for controlling the electronic device are disclosed. The electronic device of the disclosure includes a microphone, a memory storing at least one instruction, and a processor configured to execute the at least one instruction. The processor, by executing the at least one instruction, is configured to: obtain second voice data by inputting first voice data input via the microphone to a first model trained to enhance sound quality, obtain a weight by inputting the first voice data and the second voice data to a second model, and identify input data to be input to a third model using the weight.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-readable storage media, for providing information cards using semantic graph data. In some implementations, semantic graph data for a semantic graph is stored, where the semantic graph data indicates objects and relationships among the objects, and the objects include a card object that represents characteristics of an information card. A request is received from a client device, and the request is processed using the semantic graph data. Data for the information card is provided to the client device based on the card object indicated by the semantic graph data.

Abstract: Technologies are provided for automated quality assessment of translations. In some embodiments, quality of a translation can be assessed by generating a machine-learning (ML) model that classifies the translation as pertaining to one of three quality categories. A first quality category can include, for example, translations that are deemed satisfactory. A second quality category can include, for example, translations that are deemed subject to edition prior to being deemed satisfactory. A third quality category can include, for example, translations that are deemed unsatisfactory. The generated ML model can then be applied to the translation and a corresponding sentence in a source language in order to classify the translation as pertaining to one of the three categories.

Abstract: A system and method for implementing a machine learning-based virtual dialogue agent includes computing an input embedding based on receiving a user input; computing, via a pre-trained machine learning language model, an embedding response inference based on the input embedding; searching, based on the embedding response inference, a response imprintation embedding space that includes a plurality of distinct embedding representations of potential text-based responses to the user input, wherein each of the plurality of distinct embedding representations is tethered to a distinct human-imprinted media response, and searching the response imprintation embedding space includes: searching the response imprintation embedding space based on an embedding search query, and returning a target embedding representation from the response imprintation embedding space based on the searching of the response imprintation embedding space; and executing, via a user interface of the machine learning-based virtual dialogue agent,

Abstract: Embodiments relate to an intelligent computer platform to selectively amend one or more document elements. A first document is subjected to natural language processing (NLP) and two or more document characteristics are subjected to an assessment to produce a characteristic value. The document characteristics and corresponding characteristic values are analyzed to produce a characteristic profile for each identified document characteristic. Upon receipt of a new document, document characteristic data and corresponding characteristic value(s) are identified. The corresponding characteristic value(s) of the new document is applied against the produced characteristic profile. New document characteristic data is selectively amended responsive to the comparison, and a new document version is created from the selective amendment.

Abstract: Systems and processes for operating an intelligent automated assistant are provided. In one example process a set of words including a grammatical error is received. The process can generate, using a neural network based on the set of words including the grammatical error and a reference set of words, a transformed set of words and further determine, based on the set of words including the grammatical error and the reference set of words, a reconstructed reference set of words. The process can also determine, based on a comparison of the transformed set of words and the reconstructed reference set of words, whether the transformed set of words is grammatically correct and provide an indication of whether the transformed set of words is grammatically correct to the neural network.

Abstract: An image processing apparatus according to the present invention includes an image forming unit configured to form an image, a measuring unit configured to measure the formed image, a control unit configured to control execution of a single-color calibration to be performed to correct reproduction characteristics of a single-color formed by the image forming unit based on a measuring result of a single-color image formed with a single-color recording agent and execution of a multi-color calibration to be performed to correct reproduction characteristics of a multi-color image formed by the image forming unit based on a measuring result of a multi-color formed with a plurality of recording agents, and a selection unit configured to select whether to cause the control unit to perform the multi-color calibration after completing the single-color calibration or cause the control unit to perform any one of the single-color calibration and the multi-color calibration.