Abstract: A device may receive a first command, included in a set of commands, to set a configuration parameter associated with performing feature extraction. The device may receive a second command, included in the set of commands, to set a corresponding value for the configuration parameter. The configuration parameter and the corresponding value may correspond to a particular feature metric that is to be extracted. The device may configure, based on the configuration parameter and the corresponding value, feature extraction for a corpus of documents. The device may perform, based on configuring feature extraction for the corpus, feature extraction on the corpus to determine the particular feature metric. The device may generate a feature vector based on performing the feature extraction. The feature vector may include the particular feature metric. The feature vector may include a feature identifier identifying the particular feature metric. The device may provide the feature vector.

Abstract: A virtual agent with a dialogue management system and a method of training the dialogue management system is disclosed. The dialogue management system is trained using a deep reinforcement learning process. Training involves obtaining or simulating training dialogue data. During the training process, actions for the dialogue management system are selected using a Deep Q Network to process observations. The Deep Q Network is updated using a target function that includes a reward. The reward may be generated by considering one or more of the following metrics: task completion percentage, dialogue length, sentiment analysis of the user's response, emotional analysis of the user's state, explicit user feedback, and assessed quality of the action. The set of actions that the dialogue management system can take at any time may be limited by an action screener that predicts the subset of actions that the agent should consider for a given state of the system.

Abstract: A system and method for spoken language understanding using recurrent neural networks (“RNNs”) is disclosed. The system and method jointly performs the following three functions when processing the word sequence of a user utterance: (1) classify a user's speech act into a dialogue act category, (2) identify a user's intent, and (3) extract semantic constituents from the word sequence. The system and method includes using a bidirectional RNN to convert a word sequence into a hidden state representation. By providing two different orderings of the word sequence, the bidirectional nature of the RNN improves the accuracy of performing the above-mentioned three functions. The system and method includes performing the three functions jointly. The system and method uses attention, which improves the efficiency and accuracy of the spoken language understanding system by focusing on certain parts of a word sequence. The three functions can be jointly trained, which increases efficiency.

Abstract: Various embodiments provide an assessment tool that enables an automated functional assessment of applications for migration to target cloud computing platforms, such as a Platform as a Service (PaaS). The technical capabilities of various types of applications in a traditional non-platform deployment are studied and support for these technical capabilities is evaluated relative to the target platform.

Abstract: A method may include receiving, by a device, an input sample of textual content. The method may include identifying, by the device, a comparison sample that is semantically similar to the input sample. The comparison sample may be identified based on a similarity score, of the comparison sample and the input sample, satisfying a semantic similarity threshold. The method may include identifying, by the device, a plurality of output samples of textual content based on acceptance information corresponding to the plurality of output samples and the comparison sample. The acceptance information may be determined based on a user input regarding similarity or relevance of the plurality of output samples and the comparison sample, and the user input may be received before the input sample is received.

Abstract: A device may receive a first textual document and a set of second textual documents. The first textual document may identify parameters. The device may process the first textual document, based on a natural language processing algorithm, to identify first values corresponding to the parameters. The device may process the plurality of second textual documents, based on the natural language processing algorithm, to identify second values corresponding to the parameters. Each of the plurality of second textual documents may be associated with one or more respective second values of the second values. The device may determine scores for the plurality of second textual documents. A score may be determined based on comparing one or more of the first values to one or more of the second values associated with a second textual document. The device may provide information identifying the plurality of second textual documents and the scores.

Abstract: According to an example, source code flow analysis may include receiving source code for an application, and identifying virtual flow documents for the application from the source code. The virtual flow documents may represent ordered sequences of method calls for the application. The source code flow analysis may further include extracting features of the virtual flow documents, determining similarity between the virtual flow documents by estimating similarities for the extracted features to determine a flow-to-flow similarity, and clustering the virtual flow documents based on the flow-to-flow similarity. The flow-to-flow similarity may be further used, for example, to generate highest priority virtual flow documents and methods for the source code.

Abstract: A device may receive a text, from a text source, in association with a request to generate an ontology for the text. The device may generate a set of word vectors from a list of terms determined from the text. The device may determine a quantity of term clusters to be generated to form the ontology based on the set of word vectors. The device may generate term clusters based on the quantity of term clusters, attributes, and/or non-hierarchical relationships. The term clusters may be associated with concepts of the ontology. The device may provide the term clusters for display via a user interface associated with a device.

Abstract: In some examples, learning based incident or defect resolution, and test generation may include ascertaining historical log data that includes incident or defect log data associated with operation of a process, and generating, based on the historical log data, step action graphs. Based on grouping of the step action graphs with respect to different incident and defect tickets, an incident and defect action graph may be generated to further generate a machine learning model. Based on an analysis of the machine learning model with respect to a new incident or defect, an output that includes a sequence of actions may be generated to reproduce, for the new incident, steps that result in the new incident, reproduce, for the new defect, an error that results in the new defect, identify a root cause of the new incident or defect, and/or resolve the new incident or defect.

Abstract: Methods and systems including computer programs encoded on a computer storage medium, for interactive content recommendation. In one aspect, a method includes receiving a request for content by a user, determining a user intent based on the received request, providing to the user a first attribute responsive to the user intent, receiving a first attribute value responsive to the first attribute, providing a second attribute, and receiving a second attribute value responsive to the second attribute. A particular content vector including a first content attribute and a second content attribute for a particular content item is identified where the first content attribute and the second content attribute sufficiently match the first attribute value and the second attribute value. The particular content item is provided as a suggested content item, and, responsive to a user selection of the particular content item, provided for presentation on the user device.

Abstract: A device may obtain text to be processed to identify a trend associated with a topic included in the text. The text may include a plurality of text sections, associated with the topic, that may be associated with a plurality of temporal intervals. The device may determine a respective context for the topic in each of the plurality of text sections. The device may calculate a first specificity score based on the respective context for the topic for one or more text sections associated with the first temporal interval. The device may calculate a second specificity score based on the respective context for the topic for one or more text sections associated with the second temporal interval. The device may identify a trend associated with the topic based on the first specificity score and the second specificity score, and may provide information that identifies the trend.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for creating structured data using data received from unstructured textual data sources. One of the methods includes receiving unstructured textual data, identifying one or more keywords in the unstructured textual data, determining one or more patterns included in the unstructured textual data using the identified keywords, identifying one or more intelligence types that correspond with the unstructured textual data using the determined patterns, and associating, for each of the identified intelligence types, a data subset from the unstructured textual data with the respective intelligence type.

Abstract: A device may identify, for a first analytics application, a first set of characteristics and obtain, for a second analytics application, a second set of characteristics. The device may determine a measure of similarity between the first analytics application and the second analytics application based on the first set of characteristics and the second set of characteristics. The device may also determine a relevance score for a feature of the first analytics application, the relevance score being based on a relevance score associated with a feature of the second analytics application. In addition, the device may determine a relevance score for a machine learning technique associated with the first analytics application, the relevance score being based on a relevance score associated with a machine learning technique associated with the second analytics application. Based on the first relevance score or the second relevance score, the device may perform an action.

Abstract: A device receives documents and previously answered questions associated with a restricted domain, and processes the documents and the previously answered questions to generate a corpus of searchable information. The device receives a question associated with the restricted domain, and processes the question, with a machine learning model or a rule-based classifier model, to determine a classification type for the question. The device manipulates the question to generate a query from the question, and processes the query, with an expansion technique, to generate an expanded query. The device utilizes the expanded query, with the corpus of searchable information, to identify candidate answers to the question, and processes the candidate answers and the classification type for the question, with a deep learning model, to generate scored and ranked candidate answers to the question. The device selects an answer from the scored and ranked candidate answers, and provides information indicating the answer.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for creating structured data using data received from unstructured textual data sources. One of the methods includes receiving unstructured textual data, identifying one or more keywords in the unstructured textual data, determining one or more patterns included in the unstructured textual data using the identified keywords, identifying one or more intelligence types that correspond with the unstructured textual data using the determined patterns, and associating, for each of the identified intelligence types, a data subset from the unstructured textual data with the respective intelligence type.

Abstract: A device may obtain text to be analyzed to determine semantic connections between sections of the text. The device may identify subject-verb-object (SVO) units included in the text, and may determine SVO unit information that describes the SVO units. The device may analyze the SVO unit information to determine semantic connection information that identifies one or more semantic connections between two or more of the SVO units. The one or more semantic connections may identify relationships between verbs associated with the two or more of the SVO units. The device may generate a semantic network based on the SVO unit information and the semantic connection information, and may provide information regarding the semantic network.

Abstract: A device may receive information associated with first and second bug reports to be classified as duplicate or non-duplicate bug reports. The device may identify first and second descriptions associated with the first and second bug reports, respectively. The first and second descriptions may be different descriptions having a shared description type. The device may identify a neural network for encoding the first and second descriptions, based on the shared description type. The device may encode the first description into a first vector using the neural network, and may encode the second description into a second vector using the neural network. The device may classify the first and second bug reports as duplicate or non-duplicate bug reports based on the first vector and the second vector. The device may perform an action based on classifying the first and second bug reports as duplicate or non-duplicate bug reports.

Abstract: A device may receive text to be processed to prioritize text sections included in the text. The device may perform one or more prioritization techniques to prioritize the text sections. The one or more prioritization techniques may include at least one of: a semantic centrality analysis that indicates a degree to which a text section is semantically related to at least one other text section, an information content analysis that indicates a degree to which the text section includes information not included in the at least one other text section, or a combined analysis based on the semantic centrality analysis and the information content analysis. The device may prioritize the text sections, to form a set of prioritized text sections, based on performing the one or more prioritization techniques. The device may provide information that identifies the set of prioritized text sections.

Abstract: A device may receive first information that identifies an input associated with a virtual agent application executing on a user device. The virtual agent application may provide an interface for a project involving a plurality of user devices. The device may determine, based on the first information that identifies the input, a first response based on second information. The device may determine, based on at least one of the first information that identifies the input or the first response and without user input, a second response. The device may provide, to the virtual agent application of the user device, fourth information that identifies at least one of the first response or the second response.

Abstract: A device may receive a source document to be processed for contextual information associated with named entities included in the source document. The device may identify a named entity included in the source document, and may identify a context of the source document. The device may identify a reference document associated with the named entity. The reference document may be different from the source document. The device may perform a semantic similarity analysis based on the context of the source document and further based on the reference document. The device may identify contextual information, included in the reference document, based on performing the semantic similarity analysis. The contextual information may relate to the context of the source document. The device may provide the contextual information.