Computer-implemented techniques for enhanced tagging of natural language queries that are initially segmented and tagged by a named entity recognition system. By doing so, enhanced tagging of a natural language query that represents a deeper understanding of the query is provided. The enhanced tagging improves the operation of search engines that use the enhanced tags by enabling the search engine to identify and return more relevant search results in answers to natural language queries.

Computer-implemented techniques for enhanced tagging of natural language queries that are initially segmented and tagged by a named entity recognition system. By doing so, enhanced tagging of a natural language query that represents a deeper understanding of the query is provided. The enhanced tagging improves the operation of search engines that use the enhanced tags by enabling the search engine to identify and return more relevant search results in answers to natural language queries.

System and method for relation extraction using adaptive thresholding and localized context pooling (ATLOP). The system includes a computing device, the computing device has a processer and a storage device storing computer executable code. The computer executable code is configured to provide a document; embed entities in the document into embedding vectors; and predict relations between a pair of entities in the document using their embedding vectors. The relation prediction is performed based on an improved language model. Each relation has an adaptive threshold, and the relation between the pair of entities is determined to exist when a logit of the relation between the pair of entities is greater than a logit function of the corresponding adaptive threshold.

The relevance of advertisements to a user's interests is improved. In one implementation, the content of a web page is analyzed to determine a list of one or more topics associated with that web page. An advertisement is considered to be relevant to that web page if it is associated with keywords belonging to the list of one or more topics. One or more of these relevant advertisements may be provided for rendering in conjunction with the web page or related web pages.

A computer or computer retrieval system implemented method for inputting and processing file feature determination information by network terminal users. It includes providing terminal users with the items of the files according to query, determining the input feature word(s) according to the prescribed operation modes and the prescribed modes on the web page on which the item sequence(s) being located or a web page linked by that web page directly. Retrieval system can process the input information to create or improve a retrieval method or database used by users which can include different feature words or classification results, therefore the search efficiency would be greatly improved

Examples associated with reading difficulty level based resource recommendation are disclosed. One example may involve instructions stored on a computer readable medium. The instructions, when executed on a computer, may cause the computer to obtain a set of candidate resources related to a source document. The candidate resources may be obtained based on content extracted from the source document. The instructions may also cause the computer to identify reading difficulty levels of members of the set of candidate resources. The instructions may also cause the computer to recommend a selected candidate resource to a user. The selected candidate resource may be recommended based on subject matter similarity between the selected candidate resource and the source document. The selected candidate resource may also be recommended based on reading difficulty level similarity between the selected candidate resource and the source document.

A computer-implemented method for decomposing a decision table includes decomposing, by a computer processor, a decision table into a first sub-table and a second sub-table. The decision table includes two or more columns, and the decomposition is based on a semantic model describing relations among the two or more columns of the decision table. The first sub-table and the second sub-table together represent the decision table.

The disclosed apparatus, systems, and methods relate to a location query mechanism that can efficiently determine whether a target entity is located within a region of interest (ROI). At a high level, the location query mechanism can be configured to represent a ROI using one or more polygons. The location query mechanism can, in turn, divide (e.g., tessellate) the one or more polygons into sub-polygons. Subsequently, the location query mechanism can use the sub-polygons to build an index system that can efficiently determine whether a particular location is within any of the sub-polygons. Therefore, when a computing device queries whether a particular location is within the region of interest, the location query mechanism can use the index system to determine whether the particular location is within any of the sub-polygons.

Examples described herein generally relate to a computer system for generating a knowledge graph storing a plurality of entities and to displaying a topic page for an entity in the knowledge graph. The computer system performs a mining of source documents within an enterprise intranet to determine a plurality of entity names. The computer system generates an entity record within the knowledge graph for a mined entity name based on an entity schema and the source documents. The entity record includes attributes aggregated from the source documents. The computer system receives a curation action on the entity record from a first user. The computer system updates the entity record based on the curation action. The computer system displays an entity page including at least a portion of the attributes to a second user based on permissions of the second user to view the source documents.

Examples disclosed herein relate to segmentation based on clustering engines applied to summaries. In one implementation, a processor segments text based on a comparison of the output of multiple clustering engines applied to multiple summarizations of documents associated with the text. The processor outputs information related to the contents of the segments.