A process including obtaining a set of natural-language text documents that discuss a topic, the set of documents containing different states of knowledge about the topic at different times. The process includes selecting an ontology from among a plurality of ontologies that correspond to different domains of knowledge, the selection being based on the ontology corresponding to a domain of knowledge including the topic. The process includes identifying concepts discussed in the documents using the ontology and detecting changes in at least some of the concepts over time based on differences between discussion of the concepts in documents authored at different times. The process includes updating natural language instructions on the topic based on the detected changes in the concepts and storing the updated natural language instructions in memory.

Provided are a query rewriting method and apparatus, a device and a storage medium, relating to the technical field of data processing and, in particular, to technical fields including artificial intelligence, speech technology, intelligent search and deep learning. The solution includes, in response to a query rewriting request, extracting at least one of context information of an original query and intention information of the original query; and determining a new query based on a machine vocabulary collection and the at least one of the context information and the intention information. The understanding degree to the new query by a machine is greater than the understanding degree to the original query by the machine.

Various embodiments are described which leverage techniques for breaking down critical ideas from an inputted phrase into concepts in order to provide a response that is more relevant to the inputted phrase. In this regard, concepts and/or concept patterns are utilized with information retrieval searching to provide more relevant and concise documents in response to an inputted phrase. In addition, concepts and/or concept patterns are utilized with respect to assessing information (e.g., documents) available in a knowledge base and building appropriate pre-defined responses to an inputted phrase.

Systems, methods, and computer readable media related to generating query variants for a submitted query. In many implementations, the query variants are generated utilizing a generative model. A generative model is productive, in that it can be utilized to actively generate a variant of a query based on application of tokens of the query to the generative model, and optionally based on application of additional input features to the generative model.

Methods, systems, and apparatus, including computer program products, for processing search query suggestions. In one aspect, a search service provides query suggestions responsive to a query suggestion request from a client device, and determines if a prediction criterion is met. The prediction criterion is independent of a user selection of a query suggestion provided in response to one or more query suggestion requests. In response to determining that the prediction criterion is met, the search system provides search results to the client device. The search results are responsive to one of the query suggestions provided in response to the query suggestion request or one or more previous query suggestion requests.

Computing technology is described herein that provides an attention mechanism, implemented by a neural network, that generates attention information based on head-specific query information and shared key and value (KV) information, without computing head-specific key information and head-specific value information, and without caching the head-specific key information and the head-specific value information in memory. This manner of operation allows the computing technology to make efficient use of processing and memory resources. In some implementations, the attention mechanism is part of decoder of an encoder-decoder system, or a standalone decoder system. In some implementations, the computing technology leverages the attention information to generate synthesized text based on input text.

Aspects of systems and methods for providing contextual and event driven insights are provided. The system monitors information about the users and their conversations. Upon receiving a natural language request for information for a topic, the system utilizes a model to extract one or more topics from the request. The system utilizes the topic to query a resource for candidate users with knowledge about the topic. The system then queries a resource to identify candidate content items associated with the topic and the candidate users. Thereafter, the system refines the candidate users and the candidate content items to identify relevant users and content items that are meaningful to the user.

A method includes obtaining an input sequence and first and second word sequences of metadata of a plurality of datasets. The method also includes determining a set of scores including first scores and second scores by determining first scores by determining a score of the first scores based on a count of the word sequence of the first word sequences in the metadata without determining a count of the input sequence. The method also includes determining second scores by determining a score of the second scores based on a count of a second sequence of the second word sequences in the metadata. The method also includes determining an additional word for a predicted sequence including the input sequence based on the set of scores and retrieving a set of datasets based on the predicted sequence.

Provided is a search service providing method of providing search results related to a search word performed by a search service providing device, the search service providing method comprising: receiving, by the search service providing device, an initial search word; determining, by the search service providing device, one or more additional search words based on the initial search word; ranking, by the search service providing device, the one or more additional search words; selecting, by the search service providing device, at least one related search word from among the one or more additional search words based on the ranking; and providing, by the search service providing device, additional search results corresponding to the at least one related search word, the initial search word, an initial search result corresponding to the initial search word, and the one or more additional search words.

Systems and methods are described to address shortcomings in a conventional conversation system via a novel technique utilizing artificial neural networks to train the conversation system whether or not to continue context. In some aspects, an interactive media guidance application determines a type of conversation continuity in a natural language conversation comprising first and second queries. The interactive media guidance application determines a first token in the first query and a second token in the second query. The interactive media guidance application identifies entity data for the first and second tokens. The interactive media guidance application retrieves, from a knowledge graph, graph connections between the entity data for the first and second tokens. The interactive media guidance application applies this data as inputs to an artificial neural network. The interactive media guidance application determines an output that indicates the type of conversation continuity between the first and second queries.