Abstract: Systems, methods, and computer storage media are provided for analyzing a large amount of social media data from a large population of social media users and constructing correlational data models between one or more events that occur within each user's timeline. Social media posts directed to personal experiences of a large number of social media users are extracted. Event timelines are generated for each of the social media users, based on their personal experiences. The event timelines are analyzed with a particular event of interest to measure correlations between events occurring within the timelines and the particular event of interest. Using the measured correlations, a correlational data model is thereby constructed. The correlational data model may be used for application to decision-making calculations by one or more systems in an active or passive manner.

Abstract: Disclosed are techniques for extracting, identifying, and consuming imprecise temporal elements (“ITEs”). A user input may be received from a client device. A prediction may be generated of one or more time intervals to which the user input refers based upon an ITE model. The user input may be associated with the prediction, and provided to the client device.

Abstract: Commanding and task completion through self-messages is described. In implementations, message actions may be automatically initiated and performed using self-messages that a user sends to the user's own accounts. In order to do so, a message analytics module operates to check messages associated with a user account and recognize self-messages addressed by the user to the user. The message analytics module further analyzes recognized self-messages to derive the intent of the user in sending the message. Different classifications may be associated with different message actions performable via the message analytics module and/or a digital assistant invoked by the message analytics module. Thus, based on the classification of a self-message into one or more particular categories, corresponding message actions that are specified for the particular categories are preformed to handle and manage the self-messages. In this manner, a user is able command a digital assistant and otherwise specify different tasks.

Abstract: Various technologies described herein pertain to predicting intrinsically diverse sessions and retrieving information for such intrinsically diverse sessions. Search results retrieved by a search engine responsive to executing a query are received. A query classifier can be employed to determine whether the query is intrinsically diverse or not intrinsically diverse based on one or more features of the query and session interaction properties. The query is intrinsically diverse when included in an intrinsically diverse session directed towards a task, where the query and disparate queries included in the intrinsically diverse session are directed towards respective subtasks of the task. An objective function can be evaluated based at least upon the query to compute an optimized value when the query is determined to be intrinsically diverse. The search results can be presented on a display screen according to the optimized value when the query is determined to be intrinsically diverse.

Abstract: A system that analyses content of electronic communications may automatically detect requests or commitments from the electronic communications. In one example process, a processor may identify a request or a commitment in the content of the electronic message; based, at least in part, on the request or the commitment, determine an informal contract; and execute one or more actions to manage the informal contract, the one or more actions based, at least in part, on the request or the commitment.

Abstract: A system that analyses content of electronic communications may automatically extract requests or commitments from the electronic communications. In one example process, a processing component may analyze the content to determine one or more meanings of the content; query content of one or more data sources that is related to the electronic communications; and based, at least in part, on (i) the one or more meanings of the content and (ii) the content of the one or more data sources, automatically identify and extract a request or commitment from the content. Multiple actions may follow from initial recognition and extraction, including confirmation and refinement of the description of the request or commitment, and actions that assist one or more of the senders, recipients, or others to track and address the request or commitment, including the creation of additional messages, reminders, appointments, or to-do lists.

Abstract: Systems, methods, and computer storage media are provided for analyzing a large amount of social media data from a large population of social media users and constructing correlational data models between one or more events that occur within each user's timeline. Social media posts directed to personal experiences of a large number of social media users are extracted. Event timelines are generated for each of the social media users, based on their personal experiences. The event timelines are analyzed with a particular event of interest to measure correlations between events occurring within the timelines and the particular event of interest. Using the measured correlations, a correlational data model is thereby constructed. The correlational data model may be used for application to decision-making calculations by one or more systems in an active or passive manner.

Abstract: Ranking search results using result repetition is described. In an embodiment, a set of results generated by a search engine is ranked or re-ranked based on whether any of the results were included in previous sets of results generated in response to earlier queries by the same user in one or more searching sessions. User behavior data, such as whether a user clicks on a result, skips a result or misses a result, is stored in real-time and the stored data is used in performing the ranking. In various examples, the ranking is performed using a machine-learning algorithm and various parameters, such as whether a result in a current set of results has previously been clicked, skipped or missed in the same session, are generated based on the user behavior data for the current session and input to the machine-learning algorithm.

Abstract: A system that facilitates ranking search results returned by a search engine in response to receipt of a query is described herein. The system includes a receiver component that receives categorical metadata pertaining to an item and categorical metadata pertaining to the query and a computation component that computes at least one of a document feature pertaining to the item, a query feature pertaining to the query, or a document-query feature pertaining to the item and the query based at least in part upon one or more of the categorical metadata pertaining to the item or the categorical metadata pertaining to the query. The system also includes a ranker component that selectively places the item in a particular location in a sequence of items based at least in part upon the at least one of the document feature, the query feature, or the document-query feature.

Abstract: Various technologies described herein pertain to using social activity data to personalize ranking of results returned by a computing operation for a user. For each of the results returned by the computing operation, a respective first affinity of the user to a corresponding result and a respective second affinity of the user to the corresponding result can be calculated and used for ranking the results. The respective first affinity of the user to the corresponding result can be calculated based on correlations between social activity data of the user and social activity data of a first group of historical users that clicked the corresponding result. Moreover, the respective second affinity of the user to the corresponding result can be calculated based on correlations between the social activity data of the user and social activity data of a second group of historical users that skipped the corresponding results.

Abstract: Measuring duplication in search results is described. In one example, duplication between a pair of results provided by an information retrieval system in response to a query is measured. History data for the information retrieval system is accessed and query data retrieved, which describes the number of times that users have previously selected either or both of the pair of results, and a relative presentation sequence of the pair of results when displayed at each selection. From the query data, a fraction of user selections is determined in which a predefined combination of one or both of the pair of results were selected for a predefined presentation sequence. From the fraction, a measure of duplication between the pair of results is found. In further examples, the information retrieval system uses the measure of duplication to determine an overall redundancy value for a result set, and controls the result display accordingly.

Abstract: Various technologies described herein pertain to predicting intrinsically diverse sessions and retrieving information for such intrinsically diverse sessions. Search results retrieved by a search engine responsive to executing a query are received. A query classifier can be employed to determine whether the query is intrinsically diverse or not intrinsically diverse based on one or more features of the query and session interaction properties. The query is intrinsically diverse when included in an intrinsically diverse session directed towards a task, where the query and disparate queries included in the intrinsically diverse session are directed towards respective subtasks of the task. An objective function can be evaluated based at least upon the query to compute an optimized value when the query is determined to be intrinsically diverse. The search results can be presented on a display screen according to the optimized value when the query is determined to be intrinsically diverse.

Abstract: A “Cross-Lingual Unified Relevance Model” provides a feedback model that improves a machine-learned ranker for a language with few training resources, using feedback from a more complete ranker for a language that has more training resources. The model focuses on linguistically non-local queries, such as “world cup” (English language/U.S. market) and “copa mundial” (Spanish language/Mexican market), that have similar user intent in different languages and markets or regions, thus allowing the low-resource ranker to receive direct relevance feedback from the high-resource ranker. Among other things, the Cross-Lingual Unified Relevance Model differs from conventional relevancy-based techniques by incorporating both query- and document-level features.

Abstract: Various technologies described herein pertain to using social activity data to personalize ranking of results returned by a computing operation for a user. For each of the results returned by the computing operation, a respective first affinity of the user to a corresponding result and a respective second affinity of the user to the corresponding result can be calculated and used for ranking the results. The respective first affinity of the user to the corresponding result can be calculated based on correlations between social activity data of the user and social activity data of a first group of historical users that clicked the corresponding result. Moreover, the respective second affinity of the user to the corresponding result can be calculated based on correlations between the social activity data of the user and social activity data of a second group of historical users that skipped the corresponding results.

Abstract: Ranking search results using result repetition is described. In an embodiment, a set of results generated by a search engine is ranked or re-ranked based on whether any of the results were included in previous sets of results generated in response to earlier queries by the same user in one or more searching sessions. User behavior data, such as whether a user clicks on a result, skips a result or misses a result, is stored in real-time and the stored data is used in performing the ranking. In various examples, the ranking is performed using a machine-learning algorithm and various parameters, such as whether a result in a current set of results has previously been clicked, skipped or missed in the same session, are generated based on the user behavior data for the current session and input to the machine-learning algorithm.

Abstract: Architecture that generates signals/features that capture the match between intent of a query and category of documents. For example, for a query intent related to “autos”, documents that belong to categories related to “Autos” receive a higher score than documents of a “computers” category. The architecture can be applied to a search ecosystem where query intent classification and document category classifier are available, learns the mapping between query intent and document category, and introduces category-match features to a ranking algorithm, thereby improving search result relevance. The architecture learns the mapping between two existing and different taxonomies to create a category match signal from which the ranking algorithm can learn. Moreover, architecture adapts to a complex ecosystem where different taxonomies on the query side and document side exist through learning a mapping score between at least two taxonomies.

Abstract: The hierarchical approach may start at the bottom of the hierarchy. As it moves up the hierarchy, knowledge from children and cousins is used to classify items at the parent. In addition, knowledge of improper classifications at a low level are raised to a higher level to create new rules to better identify mistaken classifications at a higher level. Once the top of the hierarchy is reached, a top down approach is used to further refine the classification of items.

Abstract: The subject disclosure is directed towards building one or more context and query models representative of users' search interests based on their logged interaction behaviors (context) preceding search queries. The models are combined into an intent model by learning an optimal combination (e.g., relative weight) for combining the context model with a query model for a query. The resultant intent model may be used to perform a query-related task, such as to rank or re-rank online search results, predict future interests, select advertisements, and so forth.

Abstract: A “Cross-Lingual Unified Relevance Model” provides a feedback model that improves a machine-learned ranker for a language with few training resources, using feedback from a more complete ranker for a language that has more training resources. The model focuses on linguistically non-local queries, such as “world cup” (English language/U.S. market) and “copa mundial” (Spanish language/Mexican market), that have similar user intent in different languages and markets or regions, thus allowing the low-resource ranker to receive direct relevance feedback from the high-resource ranker. Among other things, the Cross-Lingual Unified Relevance Model differs from conventional relevancy-based techniques by incorporating both query- and document-level features.

Abstract: Measuring duplication in search results is described. In one example, duplication between a pair of results provided by an information retrieval system in response to a query is measured. History data for the information retrieval system is accessed and query data retrieved, which describes the number of times that users have previously selected either or both of the pair of results, and a relative presentation sequence of the pair of results when displayed at each selection. From the query data, a fraction of user selections is determined in which a predefined combination of one or both of the pair of results were selected for a predefined presentation sequence. From the fraction, a measure of duplication between the pair of results is found. In further examples, the information retrieval system uses the measure of duplication to determine an overall redundancy value for a result set, and controls the result display accordingly.