A method of generating search suggestions includes receiving an indication of a current location of the user device. After a user accesses a search function on the user device and before the user submits a search request, the method includes determining search results associated with locations in proximity to the current location of the user device, using query log data indicating selections of past search results by users after presentation of the past search results in response to respective past queries. The method also includes determining relative positioning of the search results based on the number of users that selected each search result, determining categories associated with the search results, grouping the search results by the determined categories; and sending the grouped search results and the one or more categories associated with the search results to the user device for display according to the determined relative positioning.

A computing device is described that includes at least one processor and a memory including instructions that when executed cause the at least one processor to output for display a graphical keyboard comprising a plurality of keys, determine, based on an indication of a selection of one or more keys from the plurality of keys, inputted, determine, based on the inputted text, an information category associated with the inputted text, determine, based on the information category, a graphical symbol associated with the information category, and output, for display, the graphical symbol in a suggestion region of the graphical keyboard.

In one embodiment, a method includes receiving, from a user of an online social network, a text query comprising one or more n-grams inputted by the user. The method also includes identifying a first set of candidate keyword phrases matching the one or more n-grams of the text query, where each candidate keyword phrase in the first set includes one or more n-grams extracted from content associated with a third-party content object interacted with by the user. The method also includes calculating a rank for each of the identified candidate keyword phrases based at least in part on a social-interaction history of the user and sending, to the user in response to the user inputting the one or more n-grams of the text query, one or more suggested queries, where at least one of the suggested queries includes one of the identified candidate keyword phrases.

An apparatus and method for providing relevant search result and query terms are disclosed herein. Natural language processing of the documents and previous search session history are used to dynamically determine document relevance, queries relevant to search categories prior to start of a search session, and query to query correlations.

The present technology relates to enhancing a message with supplemental content. The system may enhance a message based on topics identified in past correspondence messages or topics anticipated based on an intended recipient of a correspondence message being drafted. The system can operate in combination or conjunction with a language prediction system, an optimizing language model, and a text input method. The systems and methods provide users with supplemental content at a time and in a specific situation, which allows for effective targeting of content.

A system implementing a method for providing sponsored information on an electronic device determines information of interest to the user as relevant information, accesses sponsored information, and provides sponsored information based on said relevant information.

Methods and systems for searching over a large corpus of data to discover relevant information artifacts based on similar content and/or relationships are disclosed. Improvements over simple keyword and phrase based searching over Internet scale data are shown. A search query may be modified or relaxed based on the search terms and a contextual relationship therebetween. The search results may be ranked based on both a data ranking corresponding to the data entries in the corpus and a query ranking corresponding to the search query and/or the modified or relaxed search query. In this manner, the accuracy and relevance of the search results is improved.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating real-time search results. In one aspect, a method includes receiving a search query from a client; determining that real time search results should be included in a user interface document responsive to the search query; generating the user interface document, including client software to cause the client to present real time search results for the query; and sending the user interface document to the client.

Technology is provided for improving digital assistant performance by generating and presenting suggestions to users for completing a task or a session. To generate the suggestions, a machine learned language prediction model is trained with features extracted from multiple sources, such as log data and session context. When input is received from a user, the trained machine learned language prediction model is used to determine the most likely suggestion to present to the user to lead to successful task completion. In generating the suggestion, intermediate suggestion data, such as a domain, intent, and/or slot, is generated for the suggestion. From the generated intermediate suggestion data for the suggestion, a surface form of the suggestion is generated that can be presented to the user. The resulting suggestion and related context may further be used to continue training the machine learned language prediction model.

The disclosed embodiments include a computer-implemented method to facilitate generating expense reports. The embodiments include causing display of a user interface on a computing device (e.g., smartphone). The user interface presents an expense report form including control elements (e.g., text entry boxes). The method further includes presenting suggestions as inputs for a selected control element such that any suggestion that is formulated based on any journey taken by the user is prioritized for display over any generic suggestion that is not formulated based on a journey taken by the user.