Embodiments are directed to organizing conversation information. Two or more machine learning (ML) models and a plurality of sentences provided from a conversation may be employed to generate insight scores for each sentence such that each insight score correlates to a probability that its sentence includes one or more of an action or a question. In response to one or more sentences having insight scores that exceed a threshold value an information score and a definiteness score may be determined for the one or more sentences. And one or more insights associated with the conversation may be generated based on the one or more sentences. A report may be generated that associates the one or more insights with one or more portions of the conversation that include the one or more sentences that are associated with the insights.

Embodiments are directed to organizing conversation information. Two or more machine learning (ML) models and a plurality of sentences provided from a conversation may be employed to generate insight scores for each sentence such that each insight score correlates to a probability that its sentence includes one or more of an action or a question. In response to one or more sentences having insight scores that exceed a threshold value an information score and a definiteness score may be determined for the one or more sentences. And one or more insights associated with the conversation may be generated based on the one or more sentences. A report may be generated that associates the one or more insights with one or more portions of the conversation that include the one or more sentences that are associated with the insights.

A system for parsing separate intents in natural language speech configured to (i) receive, from the user computer device, a verbal statement of the user including a plurality of words; (ii) translate the verbal statement into text; (iii) label each of the plurality of words in the verbal statement; (iv) detect one or more potential splits in the verbal statement; (v) divide the verbal statement into a plurality of intents based upon the one or more potential splits; and (vi) generate a response based upon the plurality of intents.

User interface information related to relevant events of interest is provided. Events can occur anywhere in a document, and may or may not be relevant to a user utilizing an assistive technology (AT) application, such as a screen reader. A provider-side signaling system component determines whether raised events are relevant to the user. In some examples, when an application makes a plurality of attribute changes in a document at once, the signaling provider batches the related events as a single transaction, and generates a generalized annotation describing the changes. The signaling provider further packages the event notification, and sends the event notification to a client-side signaling system component. The signaling client receives the notification, and determines whether to alert the user of the event(s) based on verbosity settings. The AT application is enabled to interpret the event notification and alert the user in a meaningful way.

A corpus generation device and method, the device comprising: a segmentation module, connected to at least one monolingual parallel corpus for segmenting a sentence into words and processing the segmented words by a knowledge-driven approach; a classification module, for classifying sentences having different tag sequences but the same meaning into the same sentence cluster; a mapping module, for determining the categories of sentence structures of all the sentences in the sentence cluster, recording and storing a mapping mode for transforming tags between sentence structures when different categories of sentence structures in the same sentence cluster are transformed; a sentence structure generation module, for generating sentence structures according to a first mapping mode between a first category of sentence structures in one of the sentence clusters and other categories of sentence structures in the same sentence cluster; and a corpus generation module, for nesting a word corresponding to a sequence tag to generate a new monolingual parallel corpus.

An example method involves (i) accessing first data representing text, wherein the text defines at least one position representing a particular type of grammatical break between two portions of the text; (ii) identifying, from among the at least one position, a position that is closest to a target position within the text; (iii) based on the identified position within the text, generating second data that represents a proper subset of the text, wherein the proper subset extends from an initial position within the text to the identified position within the text; and (iv) providing output based on the generated second data.

A syntax analyzing device includes: a syntax analyzing unit that analyzes syntax of a sentence received by a receiving unit, thereby acquiring a first analysis result, which is an analysis result having one or more elements constituting the sentence and parts of speech of the respective one or more elements and has one or more binary trees each having the parts of speech or the elements as nodes; a category acquiring unit that acquires categories of the respective one or more elements constituting the sentence; a category inserting unit that acquires a second analysis result in which the categories of the elements are respectively inserted between the elements and the parts of speech of the elements, which respectively correspond to the one or more categories, and constituting the first analysis result; and a learning unit that outputs the second analysis result acquired by the category inserting unit.

The present invention discloses a Tibetan character constituent analysis method, a Tibetan sorting method and corresponding devices, and relates to the field of natural language processing. The present invention is proposed to solve the problem that the existing Tibetan sorting methods have no universality or compatibility, which is inconvenient for the use of automatic computer Tibetan sorting. The technical solution provided by the present invention includes: S10, acquiring a Tibetan text to be analyzed; S20, using Tibetan characters in the Tibetan text as the input of a preset finite state automaton group; and S30, acquiring the constituents of the Tibetan characters according to a target finite state automaton, when the target finite state automaton in the finite state automaton group determines that the Tibetan characters in the Tibetan text are correctly spelled.

A system for computer-aided escalation can include and/or interface with any or all of: a set of user interfaces (equivalently referred to herein as dashboards and/or hubs), a computing system, and a set of models. A method for computer-aided escalation includes any or all of: receiving a set of inputs; and processing the set of inputs to determine a set of outputs; triggering an action based on the set of outputs; and/or any other processes.

A system for computer-aided escalation can include and/or interface with any or all of: a set of user interfaces (equivalently referred to herein as dashboards and/or hubs), a computing system, and a set of models. A method for computer-aided escalation includes any or all of: receiving a set of inputs; and processing the set of inputs to determine a set of outputs; triggering an action based on the set of outputs; and/or any other processes.