A search engine provides summary context information for search terms across many or all of the matched records. The summary information can include additional terms including single words, phrases, pairs or other groupings of words, as well as tags or other information having special meaning. Search engines or other providers can allow users to click on or otherwise select one or more of the additional terms. Such selection can be used to add the selected term(s) to a subsequent search, and/or display to the searcher examples of the selected term(s) in context of at least one of selected ones of the plurality of records. Searchers can advantageously be given an ability to set the size of the window from which the additional terms are drawn, the number of records searched.

Methods and systems are provided for determining whether a search query with an observed number of occurrences in a set of search queries is a local search query. In accordance with one implementation, a method is provided that comprises determining an expected number of occurrences of a search query and comparing the expected number of occurrences to a threshold. Further, the method includes determining whether the search query is a local search query based, at least in part, on the comparison.

This disclosure relates to system and method for generating an optimized result set based on vector based relative importance measure (VRIM). In one embodiment, the method comprises determining a vector representation for each of a plurality of input keywords extracted from an input query, and determining a plurality of representative keywords corresponding to the plurality of input keywords from a keyword database based on the vector representation for each of the plurality of input keywords and a vector representation for each of a plurality of keywords in the keyword database. The method further comprises determining a score for a plurality of response candidates corresponding to the input query based on a relative importance score and a similarity score for each of the plurality of representative keywords present in the plurality of response candidates, and generating a result set from the plurality of response candidates based on the score.

Distributing content markings includes receiving, from a first entity, marking content corresponding to Internet content and author presentation instructions associated with the marking content. When a request to view the Internet or marking content is received from a second entity, the received author presentation instructions are used to determine whether the second entity is approved to view marking content associated with the requested Internet content. Dependent on whether the second entity is approved to view the marking content, presentation of the information associated with the marking content concurrently with the requested Internet content is enabled.

Content of different formats may be sourced from various data sources such as content servers and ingested into a data integration server by an ingestion broker embodied on a non-transitory computer readable medium. The ingestion broker may normalize the content of different formats into a uniform representation that can be indexed and delivered across multiple digital channels for a variety of applications. The normalized content may be analyzed and semantic metadata may be determined from the normalized content. The normalized content can be semantically enriched by associating the semantic metadata and the like with the content. The semantic metadata can be stored in a semantic index that can be used for searching via the data integration server. During search, the semantic metadata can be instantiated as facets for user navigation and refinement of search criteria and additional semantic relationships can be assigned to the words in the normalized content.

Systems and methods are provided for, in response to determining that a user has not elected to opt into (or that the user has elected to opt out of) the privacy policy, using limited functionality of an electronic search system to select data items from a set of candidate data items to be transmitted using a first selection criteria (which is not based on personal information of the user). The system and methods may be further configured to, in response to determining that the user has elected to opt into (or that the user has elected not to opt out of) the privacy policy, access personal information of the user, and use full functionality of the electronic search system to select data items from the same set of candidate data items based at least in part on the accessed personal information about the user.

A system and method for operating the same includes a language processing module generating a search request text signal and determining identified data from the search request text signal. A search module generates search results in response to the search request text signal. A dialog manager classifies the search request text signal into a response classification associated with a plurality of templates, selects a first template from the plurality of templates in response to the response classification and corrects search results in response to the identified data and the template to form a corrected response signal. A device receives and displays the corrected response signal.

Generating expanded responses that guide continuance of a human-to computer dialog that is facilitated by a client device and that is between at least one user and an automated assistant. The expanded responses are generated by the automated assistant in response to user interface input provided by the user via the client device, and are caused to be rendered to the user via the client device, as a response, by the automated assistant, to the user interface input of the user. An expanded response is generated based on at least one entity of interest determined based on the user interface input, and is generated to incorporate content related to one or more additional entities that are related to the entity of interest, but that are not explicitly referenced by the user interface input.

Methods, systems, and computer program products for iterative answer and supplemental information extraction for machine reading comprehension are provided herein. A computer-implemented method includes obtaining a user query and items of context information related to the user query; identifying at least one of the items of context information to be used in connection with generating supplemental information by processing the user query and at least a portion of the multiple items of context information; generating the answer using an artificial intelligence-based question answering system; generating a modified version of the user query based on keywords derived from the generated answer and keywords derived from the user query; generating items of supplemental information for the generated answer by processing the modified version of the user query and the at least one identified item of context information; and performing automated actions based on the items of supplemental information.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating subqueries from a query. In one aspect, a method includes obtaining a query, generating a set of two subqueries from the query, where the set includes a first subquery and a second subquery, determining a quality score for the set of two subqueries, determining whether the quality score for the set of two subqueries satisfies a quality threshold, and in response to determining that the quality score for the set of two subqueries satisfies the quality threshold, providing a first response to the first subquery that is responsive to a first operation that receives the first subquery as input and providing a second response to the second subquery that is responsive to a second operation that receives the second subquery as input.