A method for creating a question answering system includes receiving user stories, wherein each of the user stories is structured as a plurality of first phrasal entities within a template; applying a Natural Language Processing to discover first data relationships between the first phrasal entities and first context relationships between the first phrasal entities; constructing a knowledge graph that captures second data relationships and second contextual relationships of a plurality of second phrasal entities; enriching the KG by linking the first phrasal entities to the second phrasal entities to form enriched phrasal entities in the KG; receiving a selection of ones of the enriched phrasal entities for completing a story template; identifying a technical requirement based on the selection of the enriched phrasal entities; and training a model matching at least one of the user stories to the technical requirement.

One or more computing devices, systems, and/or methods are provided. In an example, a conversation path associated with a revised code segment of a conversational interaction entity is identified by a processor. The conversation path has a predetermined intent. A conversational phrase is generated by the processor for the conversation path. The conversational interaction entity is employed by the processor using the conversation path and the conversational phrase to generate a resultant intent. An issue report is generated by the processor for the conversational interaction entity responsive to the resultant intent not matching the predetermined intent.

A method is provided comprising: obtaining a counterparty contract, the counterparty contract including a contract that is being proposed by a counterparty to a user; performing a segmentation of the counterparty contract to identify a plurality of sentence clusters, each of the sentence clusters corresponding to a different provision in the counterparty contract; generating a plurality of counterparty provision vectors based on the counterparty contract, each of the counterparty provision vectors being generated based on a different one of the plurality of sentence clusters; retrieving a user provision vector, the user provision vector corresponding to a user provision; calculating a plurality of similarity scores for the user provision vector; detecting whether the plurality of similarity scores satisfies a condition that is associated with the user provision; and outputting a notification associated with the user provision when the condition is satisfied.

Disclosed are techniques for extracting, identifying, and consuming imprecise temporal elements (“ITEs”). A user input may be received from a client device. A prediction may be generated of one or more time intervals to which the user input refers based upon an ITE model. The user input may be associated with the prediction, and provided to the client device.

This disclosure relates to extraction of tasks from documents based on a weakly supervised classification technique, wherein extraction of tasks is identification of mentions of tasks in a document. There are several prior arts addressing the problem of extraction of events, however due to crucial distinctions between events-tasks, task extraction stands as a separate problem. The disclosure explicitly defines specific characteristics of tasks, creates labelled data at a word-level based on a plurality of linguistic rules to train a word-level weakly supervised model for task extraction. The labelled data is created based on the plurality of linguistic rules for a non-negation aspect, a volitionality aspect, an expertise aspect and a plurality of generic aspects. Further the disclosure also includes a phrase expansion technique to capture the complete meaning expressed by the task instead of merely mentioning the task that may not capture the entire meaning of the sentence.

This disclosure relates to extraction of tasks from documents based on a weakly supervised classification technique, wherein extraction of tasks is identification of mentions of tasks in a document. There are several prior arts addressing the problem of extraction of events, however due to crucial distinctions between events-tasks, task extraction stands as a separate problem. The disclosure explicitly defines specific characteristics of tasks, creates labelled data at a word-level based on a plurality of linguistic rules to train a word-level weakly supervised model for task extraction. The labelled data is created based on the plurality of linguistic rules for a non-negation aspect, a volitionality aspect, an expertise aspect and a plurality of generic aspects. Further the disclosure also includes a phrase expansion technique to capture the complete meaning expressed by the task instead of merely mentioning the task that may not capture the entire meaning of the sentence.

This application relates to a text classification method. The method includes obtaining, by a computer device, a to-be-classified text, and calculating an original text vector corresponding to the text; determining, by the computer device according to the original text vector, an input text vector corresponding to each channel of a trained text classification model; inputting, by the computer device, the input text vector corresponding to each channel into a convolution layer of the corresponding channel of the trained text classification model, the trained text classification model comprising a plurality of channels, each channel being corresponding to a sub-text classification model, and the trained text classification model being used for determining a classification result according to a sub-classification parameter outputted by each sub-text classification model; and obtaining, by the computer device, a classification result outputted by the trained text classification model, and classifying the text according to the classification result.

This application relates to a text classification method. The method includes obtaining, by a computer device, a to-be-classified text, and calculating an original text vector corresponding to the text; determining, by the computer device according to the original text vector, an input text vector corresponding to each channel of a trained text classification model; inputting, by the computer device, the input text vector corresponding to each channel into a convolution layer of the corresponding channel of the trained text classification model, the trained text classification model comprising a plurality of channels, each channel being corresponding to a sub-text classification model, and the trained text classification model being used for determining a classification result according to a sub-classification parameter outputted by each sub-text classification model; and obtaining, by the computer device, a classification result outputted by the trained text classification model, and classifying the text according to the classification result.

A method for managing a client environment includes obtaining a notification for an application abstention by a client device, in response to the notification, performing an intent analysis on the client device using a processed client intent dataset to determine a set of reasons for the application abstention, comparing the set of reasons to an upgrade coverage dataset, identifying, based on the comparing, a set of solutions corresponding to the set of reasons, generating, based on the comparing, a specialized upgrade notification based on the set of solutions, and issuing the specialized upgrade notification to the client device.

A system and method for advanced document redaction are disclosed. According to one embodiment, a system comprises a parser that analyzes documents to identify structured, semi-structured, and unstructured data from a document. A candidates generator generates a list of words for redaction from the structured, semi-structured, and unstructured data. A replacement engine replaces one or more words from the list of words with one or more of a replacement word, random characters, and random numbers.