A method, apparatus, device, and storage medium for entity linking is disclosed. The method includes: acquiring a target text; determining at least one entity mention included in the target text; determining a candidate entity corresponding to each of the entity mention based on a preset knowledge base; determining a reference text of each of the candidate entity and determining additional feature information of each of the candidate entity; and determining an entity linking result based on the target text, each of the reference text, and each piece of the additional feature information, wherein determining the entity linking result includes determining a probability of linking each of the candidate entity to the entity mention based on a splicing of a first embedding vector and a second embedding vector of the target text and a splicing of a first embedding vector and a second embedding vector of each respective reference text.

An information processing apparatus including circuitry. The circuitry receives a question from one of a user terminal apparatus and an administrator terminal apparatus. The circuitry performs determination as to whether the question is transmitted from the user terminal apparatus or transmitted from the administrator terminal apparatus. The circuitry searches for one or more answers including a word included in the question. The circuitry calculates a weighting of each of the one or more answers. When the determination result indicates that the question is transmitted from the user terminal apparatus, the circuitry transmits an answer having a weighting satisfying a predetermined threshold value of the weighting to the user terminal apparatus. When the determination result indicates the question is transmitted from the administrator terminal apparatus, the circuitry generates screen information of a screen for editing at least one of one or more answers.

Provided is an information search system that enables a searcher to efficiently find information they want to know, the system including: a database (12) that stores a plurality of pieces of information that are text-searchable; a query sentence acceptance unit (26) that accepts a query sentence in a natural language format; an inputted search keyword extractor (44) that extracts an inputted search keyword from the query sentence; a retrieval executor (40) that executes retrieval processing from the database using the inputted search keyword, along with a keyword relevant to the inputted search keyword; and a keyword dictionary (30) in which words associated with categories are registered, wherein the retrieval executor acquires, from the keyword dictionary, words associated with one of the categories selected by a searcher, re-sorts information retrieved as a result of the retrieval processing, based on the acquired words, and displays the information to the searcher.

In one embodiment, a method includes receiving at a head-mounted device a speech input from a user and a visual input captured by cameras of the head-mounted device, wherein the visual input comprises subjects and attributes associated with the subjects, and wherein the speech input comprises a co-reference to one or more of the subjects, resolving entities corresponding to the subjects associated with the co-reference based on the attributes and the co-reference, and presenting a communication content responsive to the speech input and the visual input at the head-mounted device, wherein the communication content comprises information associated with executing results of tasks corresponding to the resolved entities.

Techniques for ontology linking of unstructured text as a service are described. A service may receive a request to link unstructured text to a standardized ontology, and the service may segment and tokenize the unstructured text and send the result to multiple services implementing multiple deep machine learning models trained to identify particular entities and one or more relationships between entities. The service may perform a search of the standardized ontology to identify a set of similar candidates from the standardized ontology for the detected entities and the one or more relationships, and then rank the set of similar candidates from the standardized ontology according to their similarity to the detected entities within the unstructured text. The output from the service may include a result identifying a highest ranked candidate of the set of similar candidates from the standardized ontology for the detected entities within the unstructured text.

Methods, systems and computer-readable media enable various techniques related to semantic navigation. One aspect is a technique for displaying semantically derived facets in the search engine interface. Each of the facets comprises faceted search results. Each of the faceted search results is displayed in association with user interface elements for including or excluding the faceted search result as additional search terms to subsequently refine the search query. Another aspect automatically infers new metadata from the content and from existing metadata and then automatically annotates the content with the new metadata to improve recall and navigation. Another aspect identifies semantic annotations by determining semantic connections between the semantic annotations and then dynamically generating a topic page based on the semantic connections.

There is provided systems and method for content inversion for use in user searches and product recommendations. The methods include receiving a first content, wherein the first content includes a first sentence having at least one first sentiment expression, creating a syntactic parse tree of the first sentence, identifying a first sentiment in the at least one first sentiment expression, wherein the first sentiment corresponds to a first polarity, determining a first needs expression corresponding to the first sentiment, wherein the first needs expression includes a first subject. The method may further include creating a sub-tree corresponding to the first needs expression, and grouping the content with other content having similar sub-trees.

Systems and methods for providing a threat intelligence system include a system provider device that downloads, through communication over a network and from one or more targeted websites, a plurality of images of a first environment. Based on an OCR process, the system provider device may extract a set of textual data corresponding to a subset of images of the plurality of images, where the subset of images depict text. The system provider device stores the set of textual data in an indexed and searchable database. The system provider device assigns a threat assessment score to each image based on the set of textual data, and the threat assessment score may be updated based on comparison of the set of textual data with other sets of textual data. Based on the threat assessment score being greater than a threshold value, the system provider device may generate a security alert.

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.

A computing device receives from a user a partial natural language input related to a data source. The computing device receives an additional keystroke corresponding to the partial natural language input. The partial natural language input and the additional keystroke comprise a character string. In response to the additional keystroke, the computing device generates one or more interpretations corresponding to entities in the data source. The computing device displays the interpretations. In some implementation, the character string comprises a sequence of terms, and the device displays the interpretations in a dropdown menu adjacent to the most recently entered term in the sequence. In some implementations, the dropdown menu includes a plurality of rows, each row displaying a respective data value and a respective data field corresponding to the respective data value. Some implementations display a statistical distribution of data values for a data field (displayed adjacent to the first interpretation).