Abstract: One or more servers receive a natural language query from a client device associated with a user. The one or more servers classify the natural language query as a query that seeks information previously accessed by the user. The one or more servers then obtain a response to the natural language query from one or more collections of documents, wherein each document in the one or more collections of documents was previously accessed by the user. The one or more servers generate search results based on the response. Then, the one or more servers communicate the search results to the client device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for accessing data that indicates selection preferences of a particular user, determining, first and second data sets of content items for presentation, generating a first display panel that will cause a user device to display the first data set of the first content items, generating a second display panel that will cause the user device to display the second data set of the second content items, providing, to the user device, the first display panel and the second display panel for simultaneous display on the user device, providing, to the user device, data that displays a request to select one of the first display panel or the second display panel, and receiving, from the user device, data indicating a selection of one of the first display panel or the second display panel.

Abstract: One or more servers receive a natural language query from a client device associated with a user. The one or more servers classify the natural language query as a query that seeks information previously accessed by the user. The one or more servers then obtain a response to the natural language query from one or more collections of documents, wherein each document in the one or more collections of documents was previously accessed by the user. The one or more servers generate search results based on the response. Then, the one or more servers communicate the search results to the client device.

Abstract: One or more servers receive a natural language query from a client device associated with a user. The one or more servers classify the natural language query as a query that seeks information previously accessed by the user. The one or more servers then obtain a response to the natural language query from one or more collections of documents, wherein each document in the one or more collections of documents was previously accessed by the user. The one or more servers generate search results based on the response. Then, the one or more servers communicate the search results to the client device.

Abstract: Methods, systems, and apparatus, including computer program products, for establishing preferences for sites that are explicitly identified by a user by either a textual input or an acceptance in response to a recommendation, and adjusting the presentation of search results based on these preferences.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for presenting search results. One of the methods includes obtaining, based on a search request, search results that comprise a first user profile and a second user profile. The method includes determining a popularity difference between a first popularity associated with the first user profile and a second popularity associated with the second user profile. The method includes determining that the popularity difference exceeds a threshold. The method includes based on determining that the popularity difference exceeds the threshold, causing the search results to be presented in a display area such that the first user profile is emphasized relative to the second user profile within the display area.

Abstract: Methods, systems, and apparatus, including computer program products, for establishing preferences for sites that are explicitly identified by a user by either a textual input or an acceptance in response to a recommendation, and adjusting the presentation of search results based on these preferences.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving a query initial input from a user, in response to receiving the query initial input, determining a set of personalized query suggestions based on the query initial input, the set of personalized query suggestions including one or more content-based query suggestions that reflect at least one of user data associated with the user within one or more computer-implemented services and use of the one or more computer-implemented services by the user, and transmitting instructions to display the set of personalized query suggestions to the user.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for information retrieval. In one aspect, a method includes receiving a search input including one or more search terms; determining whether the search input includes a particular token; in response to determining that the search input includes the particular token, determining whether the one or more search terms are associated with a particular social page; in response to determining that the one or more search terms are associated with the particular social page, providing the particular social page without providing search results.

Abstract: A method is performed at a server system having one or more processors and memory. The server receives a search query from a user and identifies a list of search results associated with the search query. Each search result has an initial position in the list. The server identifies a set of user-preferred search results that comprises search results in a search history of the user. Each of the user-preferred search results has been previously selected by the user for at least a predefined minimum number of times. The server identifies in the list of search results, one or more search results that are associated with at least one of the user-preferred search results and reorders the list of search results by moving each of the identified search results from its initial position by a non-zero offset. The server then provides the reordered list of search results to the user.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for suggesting documents for dissemination. In one aspect, a method includes identifying documents that have each been classified as a document that references a particular entity. An entity score specifying a measure of importance of the particular entity to the document is determined for the documents. A proper subset of the documents is selected, as suggested documents for dissemination by the particular entity based, at least in part, on the entity score. Data that identify one or more of the suggested documents is provided to an online environment maintained by the entity. A dissemination element is provided to the online environment of the particular entity. The dissemination element causes, upon user interaction by the particular entity and with the dissemination element, at least one of the suggested documents to be disseminated to one or more other entities.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for presenting search results. One of the methods includes obtaining, based on a search request, search results that comprise a first user profile and a second user profile. The method includes determining a popularity difference between a first popularity associated with the first user profile and a second popularity associated with the second user profile. The method includes determining that the popularity difference exceeds a threshold. The method includes based on determining that the popularity difference exceeds the threshold, causing the search results to be presented in a display area such that the first user profile is emphasized relative to the second user profile within the display area.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving a search query from a user, accessing a user model that is specific to the user and that includes one or more n-grams, one or more terms of the n-grams being associated with one or more annotations, the annotations indicating at least one context in which each of the one or more terms have been used, determining a user intent for the search query based on comparing one or more terms in the search query with the terms of n-grams in the user model, and receiving search results that are responsive to the search query, the search results being specific to the user intent.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving a search query from a user, accessing a user model that is specific to the user and that includes one or more n-grams, one or more terms of the n-grams being associated with one or more annotations, the annotations indicating at least one context in which each of the one or more terms have been used, annotating one or more terms in the search query to provide an annotated search query, annotations being provided from user model, and receiving search results that are responsive to the annotated search query.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving a plurality of documents, the plurality of documents being associated with a user of a plurality of users and having been generated using a plurality of computer-implemented services, determining information from the plurality of documents that is of potential interest to the user, and providing a user model that is specific to the user and that includes one or more n-grams, one or more terms of the n-grams being associated with one or more annotations, the annotations indicating at least one context in which each of the one or more terms have been used, wherein the at least one context is based on information determined from the document

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving a query initial input from a user, in response to receiving the query initial input, determining a set of personalized query suggestions based on the query initial input, the set of personalized query suggestions including one or more content-based query suggestions that reflect at least one of user data associated with the user within one or more computer-implemented services and use of the one or more computer-implemented services by the user, and transmitting instructions to display the set of personalized query suggestions to the user.

Abstract: A method is performed at a server system having one or more processors and memory. The server receives a search query from a user and identifies a list of search results associated with the search query. Each search result has an initial position in the list. The server identifies a set of user-preferred search results that comprises search results in a search history of the user. Each of the user-preferred search results has been previously selected by the user for at least a predefined minimum number of times. The server identifies in the list of search results, one or more search results that are associated with at least one of the user-preferred search results and reorders the list of search results by moving each of the identified search results from its initial position by a non-zero offset. The server then provides the reordered list of search results to the user.

Abstract: An information server identifies a list of search results associated with a search query from a user. Each search result has an initial position in the list. The information server then identifies a user profile associated with the user. In some embodiments, the user profile includes a set of user-preferred search results that is determined at least in part from the user's search history and one or more supplemental search results that are deemed similar to at least one of the user-preferred search results. Among the list of search results, the information server identifies one or more search results that are associated with the supplemental search results. Finally, the information server reorders the list of search results by moving each of the identified search results from its initial position by an offset and then provides the reordered list of search results to the user.

Abstract: A server system receives a question from an inquirer at a client. In response, the server system identifies a plurality of information items corresponding to the question. At least one of the information items has associated classification data profiling the information therein. The server system generates a profile for the question based on the classification data of the information items and identifies one or more consultants for the question among a plurality of candidates in accordance with a comparison of the question profile and the candidates' respective user profiles. The server system submits the question to at least one of the consultants for answer. After receiving an answer to the question from the consultant, the server system forwards the answer to a client for display to the inquirer.

Abstract: A server system receives a question from an inquirer at a client. In response, the server system identifies a plurality of information items corresponding to the question. At least one of the information items has associated classification data profiling the information therein. The server system generates a profile for the question based on the classification data of the information items and identifies one or more consultants for the question among a plurality of candidates in accordance with a comparison of the question profile and the candidates' respective user profiles. The server system submits the question to at least one of the consultants for answer. After receiving an answer to the question from the consultant, the server system forwards the answer to a client for display to the inquirer.