Abstract: This application relates to apparatus and methods for natural language understanding in conversational systems using machine learning processes. In some examples, a computing device receives a request that identifies textual data. The computing device applies a natural language model to the textual data to generate first embeddings. In some examples, the natural language model is trained on retail data, such as item descriptions and chat session data. The computing device also applies a dependency based model to the textual data to generate second embeddings. Further, the computing device concatenates the first and second embeddings, and applies an intent and entity classifier to the concatenated embeddings to determine entities, and an intent, for the request. The computing device may generate a response to the request based on the determined intent and entities.

Abstract: A method for controlling a robotic system includes determining a location and/or a pose of a power system component based on data received from one or more sensors, and determining a mapping of a location of a robotic system within a model of an external environment of the robotic system based on the data. The model of the external environment provides locations of objects external to the robotic system. A sequence of movements of components of the robotic system is determined to perform maintenance on the power system component based on the locations of the objects external to the robotic system and/or the location or pose of the power system component. One or more control signals are communicated to remotely control movement of the components of the robotic system based on the sequence or movements of the components to perform maintenance on the power system component.

Abstract: The disclosed subject matter relates to a system and method for providing an automated assistant that retrieves information from a knowledge base in response to a user's natural language question. A user's natural language question voice is transformed into an intermediate representation. From the intermediate representation, a cypher query is generated which may be used to query the database. The query results are provided in response to the user. The transformation into the intermediate representation is database independent while the cypher query is dependent upon the database queried.

Abstract: The disclosed subject matter relates to a system and method for providing an automated assistant that retrieves information from a knowledge base in response to a user's natural language communications. A refinement signal based on a subsequent user communication relevant to a previous search, establishes the type of search to be performed by the automated assistant in generating a response to the user communications. A reply communication to the user includes the selected results from search type selected. The types of searches are SPECIFIC, RELATIVE and NEGATION searches.

Abstract: A system and method of improving the Natural Language Understanding of a voice assistant. A first utterance is converted to text and parsed by a Bi-LSTM neural network to create a vector representing the utterance. A subsequent utterance is similarly converted into a representative vector and the two vector are combined to predict the true intent of a user's subsequent utterance in context with the initial utterance.

Abstract: The disclosed subject matter relates to a system and method for providing an automated assistant that retrieves information from a knowledge base in response to a user's natural language question. A user's natural language question voice is transformed into an intermediate representation. From the intermediate representation, a cypher query is generated which may be used to query the database. The query results are provided in response to the user. The transformation into the intermediate representation is database independent while the cypher query is dependent upon the database queried.

Abstract: The disclosed subject matter relates to a system and method for providing an automated assistant that retrieves information from a knowledge base in response to a user's natural language question. A user's natural language question voice is transformed into an intermediate representation. From the intermediate representation, a cypher query is generated which may be used to query the database. The query results are provided in response to the user. The transformation into the intermediate representation is database independent while the cypher query is dependent upon the database queried.

Abstract: An e-commerce voice representation system is provided and generally includes a server, a database, and a customer computing device. The server may generate a hierarchical ontology to semantically represent user queries generated by the customer computing device. The server may receive from the customer computing device data representing an e-commerce user query. The server may parse the e-commerce user query based on syntactic dependencies between the words in the e-commerce user query and translating those dependencies into semantic relations between the words. The received e-commerce user query may be tagged with actions, entities, and properties of the hierarchical ontology. Identified products may be linked to conceptual classes of the hierarchical ontology. Syntactic dependencies between words of the e-commerce user query may then be determined, and a semantic representation of the e-commerce user query may be generated based on the syntactic dependencies and mapping rules.

Abstract: A system and method of improving the Natural Language Understanding of a voice assistant. A first utterance is converted to text and parsed by a Bi-LSTM neural network to create a vector representing the utterance. A subsequent utterance is similarly converted into a representative vector and the two vector are combined to predict the true intent of a user's subsequent utterance in context with the initial utterance.

Abstract: This application relates to apparatus and methods for natural language understanding in conversational systems using machine learning processes. In some examples, a computing device receives a request that identifies textual data. The computing device applies a natural language model to the textual data to generate first embeddings. In some examples, the natural language model is trained on retail data, such as item descriptions and chat session data. The computing device also applies a dependency based model to the textual data to generate second embeddings. Further, the computing device concatenates the first and second embeddings, and applies an intent and entity classifier to the concatenated embeddings to determine entities, and an intent, for the request. The computing device may generate a response to the request based on the determined intent and entities.

Abstract: The disclosed subject matter relates to a system and method for providing an automated assistant that retrieves information from a knowledge base in response to a user's natural language question. A user's natural language question voice is transformed into an intermediate representation. From the intermediate representation, a cypher query is generated which may be used to query the database. The query results are provided in response to the user. The transformation into the intermediate representation is database independent while the cypher query is dependent upon the database queried.

Abstract: The disclosed subject matter relates to a system and method for providing an automated assistant that retrieves information from a knowledge base in response to a user's natural language communications. A refinement signal based on a subsequent user communication relevant to a previous search, establishes the type of search to be performed by the automated assistant in generating a response to the user communications. A reply communication to the user includes the selected results from search type selected. The types of searches are SPECIFIC, RELATIVE and NEGATION searches.

Abstract: An e-commerce voice representation system is provided and generally includes a server, a database, and a customer computing device. The server may generate a hierarchical ontology to semantically represent user queries generated by the customer computing device. The server may receive from the customer computing device data representing an e-commerce user query. The server may parse the e-commerce user query based on syntactic dependencies between the words in the e-commerce user query and translating those dependencies into semantic relations between the words. The received e-commerce user query may be tagged with actions, entities, and properties of the hierarchical ontology. Identified products may be linked to conceptual classes of the hierarchical ontology. Syntactic dependencies between words of the e-commerce user query may then be determined, and a semantic representation of the e-commerce user query may be generated based on the syntactic dependencies and mapping rules.