A document response production method, the method including: receiving, as input, a document with requests for information, wherein each request for information is a text string; displaying a user interface on the display, the user interface simultaneously displaying a document viewer area, a virtual assistant area, and a text editor area; displaying the received document in the document viewer area; receiving, as input, a selected request for information from among the requests for information; displaying, in the virtual assistant area, one or more automatically selected recommended responses to the selected request for information, and displaying, in the virtual assistant area, one or more other selectable potential responses; based on the selected request for information, automatically generating or suggesting a text string response to the selected request for information; and displaying the text string response in the text editor area.

Systems and methods for social graph data analytics to determine the connectivity between nodes within a community are provided. A user may assign user connectivity values to other members of the community, or connectivity values may be automatically harvested or assigned from third parties or based on the frequency of interactions between members of the community. Connectivity values may represent such factors as alignment, reputation, status, and/or influence within a social graph of a network community, or the degree of trust. The paths connecting a first node to a second node may be retrieved, and social graph data analytics may be performed on the retrieved paths. For example, a network connectivity value may be determined from all or a subset of all of the retrieved paths. Network connectivity values and/or other social graph data may be outputted to third-party processes, services, and ratings agencies for use in initiating automatic transactions, making automated network-based or real-world decisions, determining or verifying the identity of a node within the community, scoring or ranking nodes, or making credit-granting decisions.

Systems and methods are described herein to search for content recommendations, and in particular, for generating emoji-based metadata for content and processing an emoji-based query using the emoji-based metadata. A system identifies a content item posted via one or more social platforms. A system may retrieve a quantity of instances of a reaction to the content item. The reaction may correspond to an emoji. A system may retrieve a comment posted in association with the content item via the one or more social platforms. A system may map the comment to the emoji based on a rule. The system may generate a factor associated with the content item and the emoji based on the quantity of instances of the reaction and based on the mapping of the comment to the emoji. The system stores the factor in a database in association with an identifier of the content item to facilitate processing of an emoji-based query.

Methods, systems, and apparatus for generating data describing context clusters and context cluster probabilities, wherein each context cluster includes query inputs based on the input context for each of the query inputs and the content described by each query input, and each context cluster probability indicates a probability that at a query input that belongs to the context cluster will be selected by the user, receiving, from a user device, an indication of a user event that includes data indicating a context of the user device, selecting as a selected context cluster, based on the context cluster probabilities for each of the context clusters and the context of the user device, a context cluster for selection input by the user device, and providing, to the user device, data that causes the user device to display a context cluster selection input that indicates the selected context cluster for user selection.

A computer-implemented method and system for searching over queries, writing and performing a data query. The computer-implemented method includes analyzing the query to understand elements described in the query. Further, the computer-implemented method includes extracting aliases for expressions to identify alternate names. Furthermore, the computer-implemented method includes allowing a user to annotate the elements. Moreover, the computer-implemented method includes establishing whether the query contains content for defining a new query, and if so, then enables writing a query according to a shorthand system.

Systems and methods are described herein to search for content recommendations, and in particular, for generating emoji-based metadata for content and processing an emoji-based query using the emoji-based metadata. A system identifies a content item posted via one or more social platforms. A system may retrieve a quantity of instances of a reaction to the content item. The reaction may correspond to an emoji. A system may retrieve a comment posted in association with the content item via the one or more social platforms. A system may map the comment to the emoji based on a rule. The system may generate a factor associated with the content item and the emoji based on the quantity of instances of the reaction and based on the mapping of the comment to the emoji. The system stores the factor in a database in association with an identifier of the content item to facilitate processing of an emoji-based query.

Embodiments described herein provide a query autocompletion (QAC) framework at subword level. Specifically, the QAC framework employs a subword encoder that encodes or converts the sequence of input alphabet letters into a sequence of output subwords. The generated subword candidate sequences from the subword encoder is then for the n-gram language model to perform beam search on. For example, as user queries for search engines are in general short, e.g., ranging from 10 to 30 characters. The n-gram language model at subword level may be used for modeling such short contexts and outperforms the traditional language model in both completion accuracy and runtime speed. Furthermore, key computations are performed prior to the runtime to prepare segmentation candidates in support of the subword encoder to generate subword candidate sequences, thus eliminating significant computational overhead.

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.

A method of disambiguating user intent in conversational interactions for information retrieval is disclosed. The method includes providing access to a set of content items with metadata describing the content items and providing access to structural knowledge showing semantic relationships and links among the content items. The method further includes providing a user preference signature, receiving a first input from the user that is intended by the user to identify at least one desired content item, and determining an ambiguity index of the first input. If the ambiguity index is high, the method determines a query input based on the first input and at least one of the structural knowledge, the user preference signature, a location of the user, and the time of the first input and selects a content item based on comparing the query input and the metadata associated with the content item.

Methods, systems, and apparatus for receiving user input that invokes digital assistant functionality; obtaining screen data indicating content displayed on a screen of the computing device; determining a classification for an entity referenced in the content indicated by the screen data; determining a suggested request that refers to the entity based on the determined classification; and providing the suggested request in response to receiving the user input that invokes the digital assistant functionality.