Abstract: Techniques for outputting interactive content and processing interactions with respect to the interactive content are described. While outputting requested content, a system may determine that interactive content is to be outputted. The system may determine output data including a first portion indicating that interactive content is going to be output and a second portion representing content corresponding to an item. The system may send the output data to the device. A user may interact with the output data, for example, by requesting performance of an action with respect to the item.

Abstract: A computing device includes a processor and a memory configured to create one or more forms for an application in an environment. The processor and the memory are further configured to create one or more environment variables related to the one or more forms. The processor is further configured to utilize one or more paths to track a dependency reference between the one or more environment variables, wherein a data model includes the one or more paths and the one or more environment variables. The processor is further configured to execute the data model to recreate the dependency reference, between the one or more environment variables, for the application in a target environment.

Abstract: Intelligent agents (IA) for automatically generating responses to content within a communication session (CS) are disclosed. An IA is trained to target the responses to a user and the user's context within the CS. An IA receives CS content that includes natural language expressions encoding users' conversations and determines content features based on natural language models. The content features indicate intended semantics of the expressions. The IA identifies likely-relevant content to the targeted user, to generate a response for. Identifying such content includes determining a relevance of the content based on content features, a context of the CS, a user-interest model, and a content-relevance model. Identifying the likely-relevant content to respond to is based on the determined relevance of the content and relevance thresholds. Various responses to the identified portions of the content are automatically generated and provided based on a natural language response-generation model targeted to the user.

Abstract: A computer system, and a method at a computer system, the method including applying a mapping function to a received message to create an characteristic value, wherein the mapping function is adapted to map similar messages to similar characteristic values; comparing the characteristic value to a value associated with each of a plurality of message extractors; determining that the characteristic value does not match any value associated with the plurality of message extractors; identifying at least one message extractor from the plurality of message extractors, the identifying determining that the value associated with the message extractor and the characteristic value from the received message, when compared, satisfy a similarity criterion; and using the identified at least one message extractor to extract information from the received message.

Abstract: A travel prediction method, apparatus, device, and storage medium.

Abstract: A method includes providing audio signals of an interaction between a plurality of human speakers, the speakers speaking into electronic devices to record the audio signals. The audio signals, which are optionally combined, include agent audio and subject audio. The method further includes automatically processing the audio signals to generate a speaker separated natural language transcript of the interaction from the audio signals. For each identified question, a subject response is identified. From the agent text, it is determined whether the question asked by the at least one agent is an open question or a closed question. A decision engine is used to determine the veracity of the subject response and the subject response is flagged if the indicia of the likelihood of deception in the subject response exceeds a predetermined value.

Abstract: Some embodiments provide a non-transitory machine-readable medium that stores a program. The program parses a knowledge graph comprising a plurality of nodes and a plurality of edges to identify metadata associated with the plurality of nodes and the plurality of edges. Each edge in the plurality of edges connects a pair of nodes in the plurality of nodes. Each node in the plurality of nodes represents an entity. Each edge in the plurality of edges connecting a particular pair of nodes in the plurality of nodes represents a relationship between two entities represented by the particular pair of nodes. The program further determines a set of token definitions. The program also generates a set of syntax rules based on the identified metadata and the set of token definitions.

Abstract: Methods, systems, and devices supporting primitive-based query generation are described. A database system may receive a natural language query associated with a subset of data sets stored at the database system, determine a set of tokens included in the natural language query, and label one or more tokens of the set of tokens with one or more primitives from a set of supported primitives associated with the subset of data sets. The database system may determine a set of higher order concepts corresponding to query operations, query conditions, or both based on the one or more labeled tokens. The database system may train a neural network to learn a grammatical structure of the natural language query and generate a database query for querying the database system based on the one or more labeled tokens, the set of higher order concepts, and the neural network.

Abstract: A computer-implemented method for detecting coordinated propagation of social media content may include calculating, by a computing device, a content similarity score for each social media post in relation to other social media posts in a set of social media posts. The method may also include identifying a related subset of social media posts based on the content similarity score. Additionally, the method may include detecting one or more clusters of social media posts in the related subset by clustering social media posts based on content similarity scores and timing. Furthermore, the method may include determining that a user account associated with a social media post in a detected cluster is in a coordinated network of user accounts. Finally, the method may include performing a security action in response to determining that the user account is in the coordinated network. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: A computerized method for extracting domain specific insights from a corpus of files containing large documents comprising: breaking down large chunks of text into smaller sentences/short paragraphs in a domain specific way, identifying and removing domain noise; identifying the sentence intents of the non-noise sentences; tagging the sentences with other domain specific attributes; defining a semantic ontology using a graph database based on the sentence intents, a multitude of mini-dictionaries and domain attributes; applying a pre-defined ontology to tag documents with domain specific hashtags; and combining the hashtags using machine learning techniques into insights.

Abstract: Systems and methods for establishing communication connections using speech, such as establishing calls between speech-controlled devices, are described. A first speech-controlled device receives a communication request in the form of audio and sends audio data corresponding to the captured audio to a server. The server performs speech processing on the audio data to determine a recipient, a subject for the call, and a device associated with the recipient. The server then sends a message indicating the communication request and audio data corresponding to the communication topic to the recipient's speech-controlled device. The recipient device outputs audio to the recipient requesting whether the recipient accepts the communication request. The recipient audibly refuses or accepts the communication request, and the recipient's speech-controlled device sends an indication of the recipient's audible decision to the server.

Abstract: A language module is joint trained with a knowledge module for natural language understanding by aligning a first knowledge graph with a second knowledge graph. The knowledge module is trained on the aligned knowledge graphs. Then, the knowledge module is integrated with the language module to generate an integrated knowledge-language module.

Abstract: A set of documents related to a particular topic, industry, or entity are received. Sentences are extract from each document. The sentences are grouped into tuples of one, two, or three consecutive sentences (i.e., short text sequences). The sentence tuples are clustered based on vector representations of the sentences. For each cluster, a set of tuples that best represents or best fits the cluster is selected. These sentence tuples are fed to an ontology to determine ontological entities associated with each tuple. These determined ontological entities are associated with the clusters corresponding to each tuple. The sentence tuples associated with each cluster are labeled based on the ontological entities associated with the cluster. The labeled sentence tuples may then be used for a variety of purposes such as training a model to determine the topic of short text sequences.

Abstract: The present disclosure provides a method of charging service for a new energy vehicle in a smart city. This method is executed by a charging pile management platform. This method includes: based on the service platform, obtaining a charging request of a user by the user platform, wherein the charging request comprises a remaining power of a vehicle of the user and a position of the user; based on the charging request, determining candidate charging piles; based on queuing information of the candidate charging piles and time information for going to the candidate charging piles, sorting the candidate charging piles to determine an object charging pile; predicting a failure rate of the object charging pile, wherein the failure rate is used to determine recommendation information of the object charging pile; and based on the service platform, feeding back the recommendation information to the user through the user platform.

Abstract: A method for training a machine learning model with parallel annotations of source instances and while facilitating security of the source instances can be performed by a system that generates a coupled machine learning model from (1) a first machine learning model trained on a first set of training data comprising unannotated natural language and (2) a second machine learning model trained on populated target templates which are populated with a plurality of vocabulary words. Once formed, the coupled machine learning model is configured to transform unannotated natural language into annotated machine-readable text.

Abstract: Methods, systems, and devices are provided for detecting spam filtering. According to one aspect, the system can inject, by a server, into a client email campaign a plurality of emails for transmission to a plurality of seed email addresses separate from a plurality of non-injected emails of the client email campaign for transmission to a plurality of target email addresses. The system can detect whether the one or more injected emails were categorized as spam or not spam by each of the plurality of seed email addresses and generate a first input to an analysis module. The system can monitor a plurality of sensing signals from the non-injected emails and generate a second input to the analysis module. The analysis module can predict based on the first input and second input whether the non-injected emails are categorized as spam by the target email addresses.

Abstract: Systems and processes for word prediction using multiple contexts are provided. For example, a plurality of words are received. A first word context including a first plurality of received words, and a second word context corresponding to the first plurality of received words and a second plurality of received words, are obtained. A first current word probability is determined based on a first language model using the first word context. A second current word probability is determined based on a second language model using the second word context. A third current word probability is determined based on the second language model using the first word context. A fourth current word probability is determined based on the first current word probability, the second current word probability, and the third current word probability. An output is provided, to a user, including a current word prediction based on the fourth current word probability.

Abstract: Various embodiments discussed herein enable client applications to be heavily integrated with a voice assistant in order to both perform commands associated with voice utterances of users via voice assistant functionality and also seamlessly cause client applications to automatically perform native functions as part of executing the voice utterance. For example, some embodiments can automatically and intelligently cause a switch to a page the user needs and automatically and intelligently cause a population of particular fields of the page the user needs based on a user view context and the voice utterance.

Abstract: A method, computer system, and a computer program product for natural language processing are provided. A first text corpus that includes semi-structured content that includes hierarchical nodes may be received. Some of the hierarchical nodes may be masked. Node embeddings and level embeddings may be generated from the semi-structured content of the first text corpus and from the masked hierarchical nodes. The node embeddings and the level embeddings may be included in a bi-directional transformer model. The bi-directional transformer model may be trained on the first text corpus by reducing loss from the bi-directional transformer model predicting the masked hierarchical nodes.

Abstract: The present disclosure discloses an entity recognition model training method and an entity recognition method as well as an apparatus using them. The entity recognition model training method includes: obtaining a training text and matching the training text with a database to obtain a plurality of matching results; processing the matching results to obtain a plurality of feature vectors corresponding to the matching results; obtaining a word vector of each word in the training text by processing the training text; and training an initial entity recognition model based on the feature vector and the word vector to obtain an entity recognition model. By using this training manner, the entity recognition model obtained can have an improved accuracy of entity recognition.

Abstract: An information processing apparatus according to the present invention includes: an acceptance unit that accepts a process request to an operation system; a specifying unit that, based on the process request, specifies an operation task to be executed in the operation system; an extraction unit that performs text analysis on the process request and extracts an answer item corresponding to an input item required at execution of the operation task from the process request; and an execution unit that executes the operation task based on the answer item.

Abstract: Example apparatus, computer-implemented methods, systems, devices, and computer-readable media facilitate concurrent consumption of media content by multiple users using superimposed animation. An example apparatus includes a display to present media and a visual representation of a person; a sensor; machine-readable instructions; and processor circuitry to execute the machine-readable instructions to at least identify a direction of a gaze of a user based on signals output by the sensor; responsive to the direction of the gaze of the user being toward the media, cause a first adjustment to the visual representation; and responsive to the direction of the gaze of the user being toward the visual representation, cause a second adjustment to the visual representation, the second adjustment different than the first adjustment.

Abstract: Systems and processes disclosed herein perform an automatic remediation process. The automatic remediation process may be a log-based remediation process. Systems disclosed herein may obtain log files from an information management system and determine the occurrence of errors at the information management system based on error codes included in the logs. Further, the systems may access a knowledgebase to determine whether solutions for the errors have been previously generated. The solutions may include patches or hotfixes that can be applied to the information management system without removing user-access or stopping execution of the information management system. The systems may automatically update the information management system to address the errors. Alternatively, or in addition, the systems may alert a user, such as an administrator, of the existence of a solution to the error, and whether the solution may be applied without interrupting service or access to the information management system.

Abstract: A method for processing text data includes analyzing the text data to identify a plurality of keywords. The method also includes determining whether each of the plurality of keywords already exists in one or more databases. When a keyword in the plurality of keywords is not found in the one or more databases, the method includes tagging the keyword with a plurality of characters for storage. The plurality of characters includes at least a first character to indicate a start of the tagging, a second character to indicate a corresponding database for storing the keyword, and a third character to indicate an end of the tagging. The method also includes storing the tagged keyword in the corresponding database.

Abstract: This disclosure provides systems, methods and apparatuses for converting natural language text in financial documents to mathematical operations for a financial management program. In some implementations, a computing device may obtain a first segment of computer readable text associated with a text capture in a financial document, parse only a portion of the first segment to generate a parsed segment, and determine translation information associated with the parsed segment to translate the parsed segment. The computing device may also store the parsed segment and the translation information in a data structure in memory, translate the parsed segment in the data structure based on the translation information, and output one or more computer readable mathematical operations corresponding to the translated segment. In this manner, the computing device may output the one or more computer readable mathematical operations without parsing all of the segment.

Abstract: Systems and processes for operating an intelligent automated assistant are provided. An example process includes receiving an utterance including a user request, determining, based on the user request, a domain associated with the user request, determining, based on the domain, a first subsequent user action and a second subsequent user action, determining, based on the domain, a first parameter for the first subsequent user action and a second parameter for the second subsequent user action, in accordance with a determination that a first score associated with the first subsequent user action is higher than a score associated with the second subsequent user action, selecting the first subsequent user action as a suggested subsequent user action, and providing the suggested subsequent user action.

Abstract: Embodiments of a method and an apparatus for improving a model based on a pre-trained semantic model are provided. The method may include: based on the pre-trained semantic model, obtaining an initial improved model, where semantic result information of an input vector is determined in the initial improved model based on a hash search method; and based on a model distillation method, training the initial improved model to obtain an improved model. Some embodiments can obtain the semantic result information of the input vector by performing the hash search method on the input vector, replace the original complex iterative calculation process of a semantic model, and obtain the improved model with few model parameters and high compression ratio.

Abstract: A method for processing natural language sentences and a computer understanding state machine with computer understanding state machine states are disclosed. The computer understanding state machine receives as inputs the parsed sentence including abstractions of the parsed sentence including weights of the abstractions. These inputs are used to find the best fitting state to process the input sentence. Subsequent sentences also are parsed and these are input to the state machine to allow processing of sequences of sentences.

Abstract: A man-machine conversation method includes: extracting a keyword from input information of a user; determining a candidate article according to the keyword; obtaining a plurality of sentences in the candidate article, and determining a score of each of the plurality of sentences; extracting part of the plurality of sentences based on the score of each of the plurality of sentences; and generating return information that includes the extracted part of the plurality of sentences.

Abstract: The present disclosure involves systems, software, and computer implemented methods for generating a unified semantic model identifying a user's intentions or goals within operating the system. By determining the intent and desires of the user, tasks and queries associated with or requested by the user can be more effectively optimized, automated, or otherwise improved. In some computing environments, multiple users access a database which includes a collection of software objects. The objects within the database can sometimes form a hierarchy, with a parent-child relationship among them. Traditionally, a developer creating the database and the objects within can only determine a user's intent based on the actions taken by the user within the database. The present solution provides the developer with a higher level model representing different users' intents based on observed data from a number of sources in addition to the user's interaction with the database.

Abstract: Techniques are disclosed for generating defeating textual replies. A computer-implemented method generates a first communicative discourse tree from an utterance and as second communicative discourse tree from a candidate answer derived from a search of keywords in the utterance. The method translates the first communicative discourse tree into a first logical formula from and the second communicative discourse tree into a second logical formula. The method determines that the first logical formula is a negation of the second logical formula. The method further provides the candidate answer to a user device responsive to the determining.

Abstract: A system for conducting parallelization of tasks is disclosed. The system includes an interface for receiving messages comprising a representation of logic describing two tasks to be executed in parallel, the message further comprising a content payload for use in the tasks. The system further includes a processor comprising devices running on independent machines, each device comprising a processing manager unit and at least two processing units. The processing manager is configured to parse the received messages and to distribute the at least two tasks to the at least two processing units for independent and parallel processing relative to the content payload.

Abstract: A sentence type recognition method and apparatus, an electronic device, and a storage medium are provided. The method includes: determining a target sentence from a to-be-recognized classroom teaching speech; segmenting the target sentence into a plurality of words, and processing a word vector of each of the plurality of words, to obtain semantic representation information of the target sentence; calculating, when the plurality of candidate sentence types comprise only a question and a non-question, an inner product of the plurality of pieces of dimension information and normalizing the inner product, to obtain a probability that the sentence type corresponding to the semantic representation information is the question; and determining, based on the probability, that the sentence type corresponding to the semantic representation information is the question or the non-question; determining the sentence type corresponding to the semantic representation information as a sentence type of the target sentence.

Abstract: Provided are a computer program product, system, and method for using domain specific vocabularies to spellcheck input strings. A determination is made of a determining a domain specific vocabulary comprising domain specific tokens for a user. The input strings in the input text from the user are processed to determine whether the input strings match the domain specific tokens in the domain specific vocabulary. Indication is made that input strings that are determined to match the domain specific tokens in the domain specific vocabulary are not to be spellchecked by a global vocabulary available to users across domains.

Abstract: Embodiments relate to providing at least one response to a user of a user device using a visual assistant, wherein the response is based on at least one user query. In an embodiment, the virtual assistant system receives the user query through a virtual multimedia contact, wherein the virtual multimedia contact is invoked by receiving a user command from the user through an interface. Thereafter, the virtual assistant system determines the response based on the user query. Further, the virtual assistant system selects a visual assistant (e.g., virtual character) for representing the response and subsequently provides the response to the user device using the visual assistant by transmitting the response to the user device using the visual assistant.

Abstract: A computer-implemented method includes receiving audio data corresponding to a spoken statement by a user and converting the audio data into a meaning representation of the natural language description for creating the application. The spoken statement includes a natural language description for creating an application. Moreover, the meaning representation includes one or more inferences made from the natural language description for creating the application. The method further includes publishing a functional version of the application based on the natural language description. The functional version of the application is executable to perform operations specified by the natural language description of the application.

Abstract: An electronic device is provided. The electronic device includes a microphone, a display, a camera, a processor, and a memory. The processor is configured to receive a first utterance input through the microphone. The processor is also configured to obtain first recognized data from a first image displayed on the display or stored in the memory. The processor is further configured to store the first recognized data in association with the first utterance input when the obtained first recognized data matches the first utterance input. Additionally, the processor is configured to activate the camera when the first recognized data does not match the first utterance input. The processor is also configured to obtain second recognized data from a second image collected through the camera and store the second recognized data in association with the first utterance input when the obtained second recognized data matches the first utterance input.

Abstract: Systems and methods for a boosted Latent Dirichlet Allocation model with predefined clusters and repelling force. Herein, clusters are pre-populated with seed words with amplified weights to predefine the characteristics of clusters. A repel force is also applied while assigning words to specific clusters in order to assign words more accurately to clusters in instances where clusters have similar characteristics. In addition to generating improved clustering of words, systems and methods may analyze words within queries to provide explainability output related to the performance of content or data.

Abstract: A non-transitory computer-readable recording medium storing a learning program that causes a computer to execute a process, a process includes acquiring a first input sentence and a first summary sentence into which the first input sentence is summarized, generating a second summary sentence to which the first summary sentence is partially-changed, and executing machine learning for a model to generate at least one summary sentence that corresponds to at least one input sentence, respectively, in response to an input of the at least one input sentence, such that a first probability of generating the first summary sentence in response to the input of the first input sentence becomes higher than a second probability of generating the second summary sentence in response to the input of the first input sentence, based on the first input sentence, the first summary sentence, and the second summary sentence.

Abstract: A mechanism is provided updating a knowledge base of a sentiment analysis system, the knowledge base being operable for storing natural language terms and a score value related to each natural language term, the score value characterizing the sentiment of the natural language term. Messages comprising natural language are received. Using content of the knowledge base, a decision is made as to whether at least one message of the received messages has a positive sentiment or a negative sentiment. A term is extracted from the message that is not present in the knowledge base. Based on a frequency of occurrence of the term in the received messages and the sentiment of the messages in which the term occurs, a score value of the term is calculated, and the term and the calculated score value are stored into the knowledge base.

Abstract: Implementations set forth herein relate to employing dynamic regulations for governing responsiveness of multiple automated assistant devices, and specifically the responsiveness an automated assistant to a given spoken utterance that has been acknowledged by two or more of the assistant devices. The dynamic regulations can be context-dependent and adapted over time in order that the automated assistant can accommodate assistant interaction preferences that may vary from user to user. For instance, a spoken utterance such as “stop,” may be intended to affect different assistant actions based on a context in which the user provided the spoken utterance. The context can refer to a location of the user relative to other rooms in a home, a time of day, a user providing the spoken utterance, an arrangement of the assistant devices within a home, and/or a state of each device in the home.

Abstract: A system for optimization of a block of text in accordance with a specific writing style, the system comprising a client application that implements functionality to process one or more blocks of text and a text processing system. The text processing system comprises an API and plurality of system components. The API receives requests from the client application as one or more blocks of text for optimization in accordance with a specific writing style or system. A given system component is operative to receive a given one of the one or more blocks of text from the API to return a recommendation to the client application that optimizes conformance of the given block of text in accordance with the specific writing style or system.

Abstract: The present invention relates to a system that uses natural language processing (NLP) to read data from a file and analyze the data based on user defined parameters. According to an illustrative embodiment of the present disclosure, a system can process and analyze a data file by finding trending themes across data entries. According to a further illustrative embodiment of the present disclosure, the system can search for reoccurring words/phrases based on Ngrams (i.e. n-grams). The system can be adapted to search for Ngrams of varying length depending on the information sought and can sort the results by Ngram length.

Abstract: Methods and systems for efficiently generating tagged training data for machine learning models. In conventional systems, all of the raw data (e.g., each sentence) has to be manually tagged. Instead, the methods and systems generate a representative sample for multiple portions of raw data, e.g., a representative sentence for multiple, similar sentences. Only the representative sample is tagged and used for training, thereby realizing a significant efficiency in both tagging the data and training the machine learning models.

Abstract: Natural language processing (NLP) methodologies and mechanisms are provided that include a named entity recognition (NER) computer model augmented to operate on an entity pattern embedding input feature in addition to other embedding input features. The mechanisms tokenize natural language content (NLC) to generate tokens and process a selected token in accordance with a predetermined entity pattern embedding technique to generate an entity pattern embedding input feature for the selected token. The entity pattern embedding input feature specifies a pattern of characters present in the selected token. The mechanisms process the NLC to generate the other embedding input features in accordance with other embedding techniques, and process, by the NER computer model, the other embedding input features and the entity pattern embedding input feature for the selected token to generate a predicted tag for the selected token. The predicted tag specifies a named entity type classification for the selected token.

Abstract: Disclosed is a method for performing fine-grained text sentiment analysis based on the users' harshness. According to the method, product attributes are automatically extracted according to comments in a data set, and the comments are split according to the product attributes, so as to achieve the effect of fine-grained analysis. Then, an inference model, which takes users' harshness into consideration, is used, and the inference model takes the users' harshness as hidden variables and solves same by means of an expectation-maximization (EM) algorithm, so as to obtain evaluation results of several product attributes of each product, thereby further improving the accuracy of sentiment analysis. According to the method, the problems in sentiment analysis of analysis granularity being too large and the users' harshness differing are solved, such that high-quality sentiment analysis can be performed on product comments.

Abstract: Data is received that encapsulates a document of text. The text is then segmented into a plurality of semantically coherent units using a coherence-aware text segmentation (CATS) machine learning model. Data is then provided that characterizes the segmenting. Related apparatus, systems, techniques and articles are also described.

Abstract: Techniques are described herein for selecting, curating, normalizing, enriching, and synthesizing the results of user experience (UX) tests. In some embodiments, a system identifies a set of expectation elements associated with one or more UX tests. An expectation element may specify, using unstructured data that does not conform to a schema, an expectation for a user experience and a respective outcome for the user experience. A themer model may generate predictions that map the respective expectation elements to a theme from a theme schema, which may include a plurality of themes. A selector model may generate selection scores for the expectation elements. The predicted themes and selection scores may be used to render user interfaces and/or trigger other actions directed to optimizing a product's design.

Abstract: This disclosure relates to a system and method for quantitative measure of subject specific sentiment analysis of a text input. The text input comprises subjects and objects. The text input is tokenized, and each word of the tokenized text input is tagged based on a part-of-speech (POS) and a universal dependency tag. A universal dependency tag tree is prepared based on dependency tags. Further, the subjects and objects are identified using a subject-verb-object (SVO) detection. The universal dependency tree is analyzed for each identified subject to determine a token dependency of the subject. The identified subject is quantified using a deep learning-based sentiment analyzer and finally a sentiment score is recommended for the subject using a probability score and a class score is assigned to the subject.

Abstract: A computer system adapts processing of expressions by a command-line interface. An expression provided to the command-line interface is analyzed, wherein the command line interface includes pre-defined expression processing. One or more artificial intelligence agents are selected from a plurality of artificial intelligence agents based on the analysis of the expression. The expression is evaluated by the selected one or more artificial intelligence agents to determine processing modifications for the pre-defined expression processing. The expression is processed in accordance with the determined processing modifications and results are provided to the command-line interface. Embodiments of the present invention further include a method and program product for adapting processing of expressions by a shell in substantially the same manner described above.