Abstract: A computing device may receive a search query and access a plurality of content objects associated with a system based on the search query. The computing device may determine a plurality of explanation vectors (e.g., comprising characteristics of a user) based on the plurality of content objects. The plurality of explanation vectors may correspond to at least one content object of the plurality of content objects. The computing device may determine a similarity score between a first object of the plurality of content objects and a second object of the plurality of content objects. The similarity score may be determined based at least in part on a first explanation vector corresponding to the first object and a second explanation vector corresponding to the second object. A response including the second object to the search query may be transmitted by the computing device based on the similarity score.

Abstract: In one embodiment, a method includes receiving a message sent from a first client system associated with a first user to a second client system associated with a second user. The method includes parsing the message to identify one or more intents to offer information and one or more slots comprising values for information for a future event extracted from the message. The method includes sending, to the second client system, instructions for presenting a suggestion to execute a task associated with the future event. The suggestion references the values for information for the future event. The method includes receiving, from the second client system, an indication that the second user selected to execute the task associated with the future event. The method includes sending, to the second client system, instructions for presenting results of the executed task associated with future event.

Abstract: In one embodiment, a method includes receiving, from a first client system associated with a first user, a message sent from the first user to a second user comprising one or more n-grams; automatically tagging, responsive to identifying the one or more named-entities, one or more of the n-grams of the message with references to the one or more identified named-entities; sending, to a second client system associated with the second user, instructions for presenting the message to the second user, where the message comprises the one or more tagged n-grams corresponding to the one or more identified named-entities, where each tagged n-gram is selectable to execute a task associated with the corresponding identified named-entity; receiving, from the second client system, an indication that the second user selected one or more tagged n-grams to execute the task associated with the corresponding identified named-entity; and sending, to the second client system, instructions for presenting results of the executed t

Abstract: In one embodiment, a method includes accessing a mention table of entries that each have: (1) a string, (2) a count of a number of times the string is used in a corpus, and (3) a count of a number of times the string is linked to another document. The method also includes calculating, for each n-gram of a search query from a querying user, a link probability that represents the likelihood that the n-gram corresponds to an entity associated with a communication network. The method also includes identifying content objects that match the search query and ranking the content objects based at least in part on on the calculated link probability. The method also includes sending instructions to present the search results on a client system of the querying user.

Abstract: In one embodiment, a method includes receiving, from a first client system associated with a first user, a message sent from the first user to a second user, analyzing the message from the first user to identify one or more intents and one or more slots of the received message, computing a confidence score for the intent to offer entity information based on user behavior history records associated with the second user, sending, to a second client system associated with the second user, if the confidence score exceeds a threshold score, instructions for presenting a suggestion to the second user to store the values for entity information in association with a profile record for the entity, and receiving, from the second client system associated with the second user, an indication from the second user confirming the values for entity information should be stored with the profile record for the entity.

Abstract: In one embodiment, a method includes receiving, from a first client system associated with a first user, a message sent from the first user to a second user, where the message includes one or more n-grams, analyzing the received message to identify one or more named-entities corresponding to one or more of the n-grams, tagging one or more of the n-grams of the message with references to the one or more identified named-entities, and sending, to a second client system associated with the second user, instructions for presenting the message to the second user, where the message includes the one or more tagged n-grams corresponding to the one or more identified named-entities, where each tagged n-gram is selectable to retrieve additional information associated with the corresponding named-entity.

Abstract: In one embodiment, a method includes accessing a document, identifying one or more noun phrases in the document by performing a pre-processing on the accessed document, generating, for each identified noun phrase, a list of candidate entities corresponding to the noun phrase, wherein the list of candidate entities is looked up in an entity index using the noun phrase, computing, for each candidate entity corresponding to each identified noun phrase, a confidence score that the noun phrase is intended to reference the candidate entity by analyzing the accessed document by a machine learning model, constructing a pool of mention-entity pairs for the accessed document, filtering the pool of mention-entity pairs by removing each mention-entity pair from the pool based on their computed confidence scores, and storing the post-filtered pool of mention-entity pairs in a data store in association with the accessed document.

Abstract: In one embodiment, a method includes accessing a mention table of entries that each have: (1) a string, (2) a count of a number of times the string is used in a corpus, and (3) a count of a number of times the string is linked to another document. The method also includes calculating, for each n-gram of a search query from a querying user, a link probability that represents the likelihood that the n-gram corresponds to an entity associated with a communication network. The method also includes identifying content objects that match the search query and ranking the content objects based at least in part on on the calculated link probability. The method also includes sending instructions to present the search results on a client system of the querying user.

Abstract: Systems, methods, and computer-readable storage media for presenting supplemental search results having indications that identified documents have been endorsed by the user and/or social network connections of the user are provided. A search query is received and it is determined that the user's social networking data is available. Documents that have been endorsed by the user and/or social network connections of the user are searched to identify those that satisfy the input search query. The satisfying documents are assigned a relevance score to determine whether each satisfying document is relevant enough to be shown and to determine placement of the document on the SERP relative to standard search results. Upon rendering of the SERP, a supplemental search result identifying documents that were endorsed by the user and/or social network connections of the user is presented, as is an indication about which social network connection(s) of the user endorsed the document.

Abstract: Improved, personalized searching through the use of personal connection graphs is presented. Responsive to receiving a search query, the search engine obtains a user sketch (representing a user's connection graph) and obtains search results responsive to the search query and also based, in part, as a function of a relationship distance between the user and the referenced content as determined by the user sketch. One or more search results pages are generated from the obtained search results and returned to the user.

Abstract: Systems, computer-readable media, and methods for tagging documents based on a graph pertaining to one or more entities which a user has included in a search query. The user may have at least one social networking relationship with the entity. A search engine is configured to display a search engine results page in response to the search query received from the user. The search engine may also receive suggested tags that identify documents that could be linked to the entity identified in the query. The user may confirm that the suggested tags are appropriate via feedback that is transmitted to the search engine. In turn, the search engine updates a graph to reflect a number of users that agree with the suggested tag.

Abstract: Systems, computer-readable media, and methods for utilizing information pertaining to one or more individuals or entities with which a user has at least one social networking relationship are provided. A search engine is configured to receive a query, to identify matching electronic documents, to rank the electronic documents, and to transmit the matching electronic documents and/or advertisements to the user in response to receiving a query. Upon receiving the query from a user, the search engine obtains a social network identifier of the user and utilizes information about the user's social networking relationships to augment the query with nonretrieval modifiers. The search engine processes the nonretrieval modifiers matching the electronic documents included in search results and ranks the results but does not use the nonretrieval modifiers to identify or retrieve results matching the query. The ranked electronic documents are included in the results and displayed in rank order to the user.

Abstract: Systems, methods, and computer-readable storage media for tagging uniform resource locators (URLs) included in a search engine results page are provided. Upon receipt of a search query that includes a name of an entity, the server device provides search results and entry fields to tag one or more URLs that correspond to the entity. The server device obtains a social network of the user that provided the query. The server device processes the social network to locate entities that match the query and that are within a threshold number of hops. The user may tag one or more URLs with social network account information for the entities based on authorization information received from an owner that manages the social network account.

Abstract: Systems, methods, and computer-readable storage media for presenting supplemental search results having indications that identified documents have been endorsed by the user and/or social network connections of the user are provided. A search query is received and it is determined that the user's social networking data is available. Documents that have been endorsed by the user and/or social network connections of the user are searched to identify those that satisfy the input search query. The satisfying documents are assigned a relevance score to determine whether each satisfying document is relevant enough to be shown and to determine placement of the document on the SERP relative to standard search results. Upon rendering of the SERP, a supplemental search result identifying documents that were endorsed by the user and/or social network connections of the user is presented, as is an indication about which social network connection(s) of the user endorsed the document.

Abstract: Systems, methods, and computer-readable storage media for presenting results of search queries with indications that at least a portion of such results has been endorsed by the user and/or social network connections of the user, are provided. Upon receipt of a search query, Web search results satisfying the query are determined. Satisfying search results that have been endorsed by the requesting user and/or one or more social network connections of the requesting user are identified. Upon presentation of the search results on the SERF, those results that were identified as having been endorsed by the requesting user and/or one or more social network connections of the requesting user are annotated as such. In this way, the requesting user may be able to more readily identify personally relevant results as the annotated results have been indicated to be preferences of the user and/or his or her social network connections.

Abstract: The present invention is directed towards system and methods for generating a visual representation indicating performance of a system capable of accepting one or more inputs and producing an ordered set of one or more responsive outputs. The method of the present invention comprises selecting one or more benchmark inputs and generating an ordered output set for each of the one or more benchmark inputs, a given output set comprising one or more output items responsive to a given benchmark query. One or pixels representing the one or more output items comprising the one or more outputs sets are generated, a given pixel containing a visual representation indicating a degree to which the output item represented by the pixel is relevant with respect to the benchmark input to which the output item is responsive. The one or more pixels representing the one or more output items comprising the one or more output sets are arranged in a circle in a manner indicative of the performance of the system.

Abstract: An exemplary method for providing secure access to resources at shared appliances comprises obtaining an instruction from a first user to send a resource to a secure repository, the resource being associated with a first identifier, receiving a second identifier from a shared appliance, determining a pseudo identity associated with the shared appliance based on the second identifier, granting to the shared appliance permissions associated with the pseudo identity, including a permission to retrieve the resource from the secure repository, receiving the first identifier from a second user at the shared appliance, and enabling the shared appliance to provide the resource to the second user at the shared appliance.