Abstract: Disclosed embodiments include systems and methods relevant to improvements to natural language processing used to determine an intent and one or more associated parameters from a given input string. In an example, an input string is received and first and second different n-grams are applied to the input string. Recurrent neural network models are then used to generate output data based in part on the first and second different n-grams. Intent detection and semantic labeling are applied to the output of the recurrent neural network models.

Abstract: Described herein are systems and methods for providing hierarchical state tracking in a spoken dialogue system. A sequence of turns is received by a spoken dialogue system. Each turn includes a user utterance and a machine act. At each turn, a value pointer and a turn pointer are provided for that turn. The value pointer represents a probability distribution over the one or more words in the user utterance that indicates whether each word in the user utterance is a slot value for a slot. The turn pointer identifies which turn in a set of turns includes a currently-relevant slot value for the slot, where the set of turns includes a current turn for which the turn point is being provided, and all turns that precede the current turn.

Abstract: Examples of the present disclosure provide systems and methods relating to a machine comprehension test with a learning-based approach, harnessing neural networks arranged in a parallel hierarchy. This parallel hierarchy enables the model to compare the passage, question, and answer from a variety of perspectives, as opposed to using a manually designed set of features. Perspectives may range from the word level to sentence fragments to sequences of sentences, and networks operate on word-embedding representations of text. A training methodology for small data is also provided.

Abstract: A computer-implemented method, system using at least one computing device, and computer program product are disclosed for linking an ontology provided by a content service with a word expansion ontology. The content service ontology is referred to as a category ontology and the word expansion ontology is referred to herein as a lexical ontology. A user may provide an input such as an input command to an application. The input command is processed by a natural language processing engine to derive the user's intent and to extract relevant entities embodied in the command. The NLP engine may create a composite concept set containing multiple permutations of the concepts (entities extracted) and provide the composite concept set to a concept mapper. The concept mapper applies searches an ontology map and applies one or more scoring operations to determine a best match between the composite concept set and at least one category provided by the category ontology.

Abstract: A method, system, and computer program product provide a conversation agent to process natural language queries expressed by a user and perform commands according to the derived intention of the user. A natural language processing (NLP) engine derives intent using conditional random fields to identify a domain and at least one task embodied in the query. The NLP may further identify one or more subdomains, and one or more entities related to the identified command. A template system creates a data structure for information relevant to the derived intent and passes a template to a services manager for interfacing with one or more services capable of accomplishing the task. A dialog manager may elicit more entities from the user if required by the services manager and otherwise engage in conversation with the user. In one embodiment, the conversational agent allows a user to engage in multiple conversations simultaneously.

Abstract: A system, method and computer program for performing voice commands on a mobile device and presenting the results on an interactive timeline is disclosed. A user may utter a voice command into the microphone of their mobile device while an application is running. The voice command is processed to derive the intention of the user, specifically by determining the domain, at least one task and at least one parameter for the task from the voice command. A services component performs the task identified and presents the results on the mobile device screen. In various embodiments, the results are presented on a timeline and may be grouped together by domains and sorted by the time that the results were obtained. A search history view may also be viewed that includes search results sorted chronologically each of which is represented graphically by an icon that represents the category of each search.

Abstract: A system, method, and computer-readable medium are provided for managing a route topography in a software environment. The system includes a dashboard user interface for allowing a user to manage the services that are part of a software application. The dashboard allows the user to add and delete services for a software application, to establish a communication identifier of each service, and to clone a first route topography to create a second route topography. A routing service manages the route topography by storing a route identifier and the associated services for the route. When a user modifies an existing route topography or creates a new route topography, the information is managed by the routing service which provides the route information to requesting services upon demand. In one embodiment, each service of the software application includes a route cache with routing information that may be updated periodically by the routing service.

Abstract: Provided is a system, method and computer-readable medium for generating data that may be used to train models for a natural language processing application. A system architect creates a plurality of sentence patterns that include entity variables and initiates sentence generation. Each entity is associated with one or more entity data sources. A language generator accepts the sentence patterns as inputs, and references the various entity sources to create a plurality of generated sentences. The generated sentences may be associated with a particular class and therefore used to train one or more statistical classification models and entity extraction models for associated models. The sentence generated process may be initiated and controlled using a user interface displayable on a computing device, the user interface in communication with the language generator module.

Abstract: A method, system, and computer program product provide a conversation agent to process natural language queries expressed by a user and perform commands according to the derived intention of the user. A natural language processing (NLP) engine derives intent using conditional random fields to identify a domain and at least one task embodied in the query. The NLP may further identify one or more subdomains, and one or more entities related to the identified command. A template system creates a data structure for information relevant to the derived intent and passes a template to a services manager for interfacing with one or more services capable of accomplishing the task. A dialogue manager may elicit more entities from the user if required by the services manager and otherwise engage in conversation with the user. In one embodiment, the conversational agent allows a user to engage in multiple conversations simultaneously.

Abstract: A computer-implemented method and system and computer-readable medium are disclosed for linking an ontology provided by a content service (i.e. category ontology) with a word expansion ontology (i.e. lexical ontology). A user may provide an input such as a voice command to an application. The voice command is processed by a natural language processing (NLP) engine to derive the user's intent and to extract relevant entities embodied in the command. The NLP engine may create a composite concept set containing multiple permutations of the concepts (entities extracted) and provide the composite concept set to a concept mapper. The concept mapper searches a mapping file and applies one or more scoring operations to determine a best match between the composite concept set and at least one category provided by the category ontology. The content service is searched using the category and the results are displayed to the user.

Abstract: A method, system and non-transitory computer-readable medium are provided for improving a statistical classification system, such as a statistical classification system that accepts natural language voice queries as inputs. A clustering engine may create one or more clusters of queries where the queries in each cluster are related in some way. A reviewing module may be employed to determine whether each cluster relates to an existing category supported by the classification system, a new category that can be supported by the classification system by training statistical models with the data from the cluster, is ambiguous, or is not useful to improve the classification system. For clusters determined to be useful for improving the system, the data in the clusters may be added to an existing training set or used as a training set to train new statistical models.

Abstract: A system, method, and computer-readable medium are provided for managing a route topography in a software environment. The system includes a dashboard user interface for allowing a user to manage the services that are part of a software application. The dashboard allows the user to add and delete services for a software application, to establish a communication identifier of each service, and to clone a first route topography to create a second route topography. A routing service manages the route topography by storing a route identifier and the associated services for the route. When a user modifies an existing route topography or creates a new route topography, the information is managed by the routing service which provides the route information to requesting services upon demand. In one embodiment, each service of the software application includes a route cache with routing information that may be updated periodically by the routing service.