Provided is a method including obtaining a corpus and an associated set of domain indicators. The method includes learning a set of vectors in an embedding space based on n-grams of the corpus. The method includes updating ontology graphs comprising a set of vertices and edges associating the set of vertices with each other. The method also includes determining a vector cluster using hierarchical clustering based on distances of the set of vectors with respect to each other in the embedding space and determining a hierarchy of the ontology graphs based on a set of domain indicators of a respective set of vertices corresponding to vectors of the vector cluster. The method also includes updating an index based on the ontology graphs.

Embodiments provide for improved data sequence validity processing, for example to determine validity of sentences or other language within a particular language domain. Such improved processing is useful at least for arranging data sequences based on determined validity, and/or making determinations and/or performing actions based on the determined validity. A determined probability (e.g., transformed into the perplexity space) of each token appearing in a data sequence is used in any of a myriad of manners to perform such data sequence validity processing. Example embodiments provide for generating a perplexity value set for each data sequence in a plurality of data sequences, generating a probabilistic ranking set for the plurality of data sequences based on the perplexity value sets and at least one sequence ranking metric, and generating an arrangement of the plurality of data sequences based on the probabilistic ranking set.

Systems and techniques that facilitate keyword-object taxonomy generation and utilization are provided. In various embodiments, a system can comprise a receiver component that can access an input object class. In various aspects, the system can comprise a taxonomy component that can output one or more keyword combinations that are non-redundant and relevant to the input object class, based on querying a keyword-object taxonomy. In various instances, the receiver component can access (and/or be provided with an electronic link to) a set of recorded keyword combinations and a set of recorded object classes respectively corresponding to the set of keyword combinations. In various cases, the taxonomy component can generate the keyword-object taxonomy based on the set of recorded keyword combinations and the set of recorded object classes.

An approach for a non-factoid question answering framework across tasks and domains may be provided. The approach may include training a multi-task joint learning model in a general domain. The approach may also include initializing the multi-task joint learning model in a specific target domain. The approach may include tuning the joint learning model in the target domain. The approach may include determining which task of the multiple tasks is more difficult for the multi-task joint learning model to learn. The approach may also include dynamically adjusting the weights of the multi-task joint learning model, allowing the model to concentrate on learning the more difficult learning task.

Systems, devices, computer-implemented methods, and/or computer program products that facilitate generative relation linking for question answering over knowledge bases. In one example, a system can comprise a processor that executes computer executable components stored in memory. The computer executable components can comprise a relation linking component. The relation linking component can map relations identified in a natural language question to corresponding relations of a knowledge base using a generative model.

A third-party service may be used to assist entities in responding to requests of users by determining a suggested response to a received communication. The third party service may receive a request from a first entity, such as via an application programming interface request, that includes a message in a conversation. A conversation feature vector may be computed by processing the message with a first neural network. A suggested respond to the message may be determined by processing the conversation feature vector with a second neural network. The third-party service may then return the suggested response for use in the conversation. The third-party service may similarly be used to assist other entities in responding to requests of users.

According to implementations of the subject matter described herein, a clause-based semantic parsing solution is provided. In the solution, a first clause with independent semantics is determined from a target statement. The target statement is converted to a first intermediate statement based on a first logical representation corresponding to the first clause. Subsequently, at least one logical representation corresponding to at least part of semantics of the first intermediate statement is determined. The first logical representation and the at least one logical representation may be used to determine a target logical representation corresponding to semantics of the target statement. Therefore, more accurate semantic parsing can be achieved.

Techniques for recommending a skill experience to a user after a user-system dialog session has ended are described. Upon a dialog session ending, the system uses a first machine learning model to determine potential intents to recommend to a user. The system then uses a second machine learning model to determine a particular skill and intent to recommend. The system then prompts the user to accept the recommended skill and intent. If the user accepts, the system calls the recommended skill to execute. As part of calling the skill, the system sends to the skill at least one entity provided in a natural language user input of the ended dialog session. This enables the skill to skip welcome prompts, and initiate processing to output a response based on the intent and the at least one entity of the ended dialog session.

An information processing system comprising a processor programmed to: receive a question asked by a questioner, an answer provided by an answerer to the question, and a rating by a rater with respect to at least one of the question and the answer; manage relationship information, the relationship information being related to the questioner, the answerer, and the rating by the rater; acquire attribute information about each of the questioner, the answerer, and the rater; and present rating information based on the relationship information and in response to a condition specified by a requester with respect to the attribute information.

At a first chatbot, a query expressed in natural language form is received. It is determined that responding to the query requires data external to the first chatbot. From a data source external to the first chatbot, response data corresponding to the query is obtained. Using the response data, the query is responded to in natural language form. Using the response data, the first chatbot is updated.