Abstract: Representative embodiments disclose mechanisms to map natural language input to an application programming interface (API) call. The natural language input is first mapped to an API frame, which is a representation of the API call without any API call formatting. The mapping from natural language input to API frame is performed using a trained sequence to sequence neural model. The sequence to sequence neural model is decomposed into small prediction units called modules. Each module is highly specialized at predicting a pre-defined kind of sequence output. The output of the modules can be displayed in an interactive user interface that allows the user to add, remove, and/or modify the output of the individual modules. The user input can be used as further training data. The API frame is mapped to an API call using a deterministic mapping.

Abstract: A method includes receiving an email addressed to a recipient user, processing the received email using a reparametrized recurrent neural network model to identify an action based on the received email, and wherein the reparametrized recurrent neural network model has been trained on an email dataset annotated with recipient corresponding actions and reparametrized on unannotated conversation data having structures similar to email data.

Abstract: This disclosure describes techniques and architectures that involve a latent activity model for workplace emails. Such a model is based, at least in part, on a concept that communications, such as email at a workplace, are purposeful and organized by activities. An activity is a set of interrelated actions and events around a common goal, involving a particular group of people, set of resources, and time framework, for example. The latent activity model involves a probabilistic inference in graphical models that jointly captures the interplay between latent activities and the email contexts governed by the emails. Such contexts may be email recipients, subject and body of the email, and so on.

Abstract: Various technologies pertaining to exploratory suggestions are described herein. A computer-implemented graph is constructed, where the graph includes nodes that are representative of aspects and edges that are representative of associations between aspects. An aspect is representative of a sub-topic of a topic or a sub-task of a task. The computer-implemented graph is learned based upon content of search logs, and is used to output exploratory suggestions, where a user is exploring a topic or attempting to complete a multi-step task.

Abstract: Examples of the present disclosure describe systems and methods of identifying good and bad abandonment using gesture movement. In aspects, user feedback signals may be received by a client device in response to the viewing and/or navigation of query results. The feedback signals may be provided to a framework for determining and/or analyzing query abandonment. The framework may identify gesture data in the feedback signals and extract feature data from the gesture data. The feature data may be provided to a metrics component to determine metrics and/or satisfaction values for the feature data. The metrics and/or feature data may be used to train a predictive model to identify good abandonment in query results.

Abstract: This disclosure describes techniques and architectures that involve a latent activity model for workplace emails. Such a model is based, at least in part, on a concept that communications, such as email at a workplace, are purposeful and organized by activities. An activity is a set of interrelated actions and events around a common goal, involving a particular group of people, set of resources, and time framework, for example. The latent activity model involves a probabilistic inference in graphical models that jointly captures the interplay between latent activities and the email contexts governed by the emails. Such contexts may be email recipients, subject and body of the email, and so on.

Abstract: Technologies pertaining to automatically identifying sets of query attribute values that are highly correlative with user dissatisfaction with a search engine are described. Dissatisfied queries are automatically identified through analysis of search logs, wherein a dissatisfied query is a query submitted to a search engine by a user, wherein the user was dissatisfied with search results provided by the search engine responsive to receipt of the query. Sets of query attribute values that are highly correlated with dissatisfied queries, and thus user dissatisfaction, are automatically identified based at least in part upon the identifying of the dissatisfied queries. Subsequent to identifying a set of query attribute values, a segment-specific ranker is learned that is configured to rank search results responsive to receipt of a query with the set of query attribute values, wherein the segment-specific ranker outperforms a general purpose ranker for queries having the set of query attribute values.

Abstract: Subject matter involves using natural language to Web application program interfaces (API), which map natural language commands into API calls, or API commands. This mapping enables an average user with little or no programming expertise to access Web services that use API calls using natural language. An API schema is accessed and using a specialized grammar, with the help of application programmers, canonical commands associated with the API calls are generated. A hierarchical probabilistic distribution may be applied to a semantic mesh associated with the canonical commands to identify elements of the commands that require labeling. The identified elements may be sent to annotators, for labeling with NL phrases. Labeled elements may be applied to the semantic mesh and probabilities, or weights updated. Labeled elements may be mapped to the canonical commands with machine learning to generate a natural language to API interface. Other embodiments are described and claimed.

Abstract: Biases in search and retrieval (i.e., situations where searchers seek or are presented with information that significantly deviates from the truth) may be detected by comparison to one or more authoritative sources. Once bias or potential bias is detected, techniques may be applied to indicate and/or compensate for the bias. Such techniques may allow users to more easily assess the veracity of search results, and increase the chances that users will locate accurate answers to their questions.

Abstract: Biases in search and retrieval (i.e., situations where searchers seek or are presented with information that significantly deviates from the truth) may be detected by comparison to one or more authoritative sources. Once bias or potential bias is detected, techniques may be applied to indicate and/or compensate for the bias. Such techniques may allow users to more easily assess the veracity of search results, and increase the chances that users will locate accurate answers to their questions.

Abstract: Biases in search and retrieval (i.e., situations where searchers seek or are presented with information that significantly deviates from the truth) may be detected by comparison to one or more authoritative sources. Once bias or potential bias is detected, techniques may be applied to indicate and/or compensate for the bias. Such techniques may allow users to more easily assess the veracity of search results, and increase the chances that users will locate accurate answers to their questions.

Abstract: This disclosure describes techniques and architectures that involve a latent activity model for workplace emails. Such a model is based, at least in part, on a concept that communications, such as email at a workplace, are purposeful and organized by activities. An activity is a set of interrelated actions and events around a common goal, involving a particular group of people, set of resources, and time framework, for example. The latent activity model involves a probabilistic inference in graphical models that jointly captures the interplay between latent activities and the email contexts governed by the emails. Such contexts may be email recipients, subject and body of the email, and so on.

Abstract: The claimed subject matter includes a system and method for attribution of search activity in multi-user settings. The method includes training a classifier to distinguish between machines that are single-user and multi-user based on activity logs of an identified machine. The identified machine is determined to be multi-user based on the classifier. A number of users is estimated for the identified machine. Activity of the users is clustered based on the number of users estimated. A similarity function is learned for the number of users estimated. The method also includes assigning new activity to one of the users based on the clustering, and the similarity function.

Abstract: Examples of the present disclosure describe systems and methods of identifying good and bad abandonment using gesture movement. In aspects, user feedback signals may be received by a client device in response to the viewing and/or navigation of query results. The feedback signals may be provided to a framework for determining and/or analyzing query abandonment. The framework may identify gesture data in the feedback signals and extract feature data from the gesture data. The feature data may be provided to a metrics component to determine metrics and/or satisfaction values for the feature data. The metrics and/or feature data may be used to train a predictive model to identify good abandonment in query results.

Abstract: The subject disclosure is directed towards using a satisfaction model's prediction as to whether a user was satisfied or dissatisfied in satisfying a search goal to help estimate the relevance of a URL/document that was returned and clicked by the user. The clickthrough data for a search goal session is processed by either a utility model or a despair model based on whether the satisfaction model indicated that the search goal session ended with the user satisfied or dissatisfied, respectively. The utility model distributes a utility value to each clicked URL, while the despair model distributes a despair value to each clicked URL. The utility value and despair value of each query-URL pair may be used as corresponding feature data for learning a search ranker.

Abstract: Various technologies described herein pertain to evaluating search preferences. A search query, a first search result list returned by a first ranker system responsive to the search query, and a second search result list returned by a second ranker system responsive to the search query are received. A classifier is employed to predict (e.g., based upon values of features of the search query, the first search result list, and the second search result list) whether a search preference judgment (e.g., a side-by-side search preference judgment, etc.) indicates a quality difference between the first search result list and the second search result list. The search query, the first search result list, and the second search result list are excluded from a set of search queries and search result list pairs to be manually judged for search preference judgments when predicted to lack the quality difference.

Abstract: Biases in search and retrieval (i.e., situations where searchers seek or are presented with information that significantly deviates from the truth) may be detected by comparison to one or more authoritative sources. Once bias or potential bias is detected, techniques may be applied to indicate and/or compensate for the bias. Such techniques may allow users to more easily assess the veracity of search results, and increase the chances that users will locate accurate answers to their questions.

Abstract: Biases in search and retrieval (i.e., situations where searchers seek or are presented with information that significantly deviates from the truth) may be detected by comparison to one or more authoritative sources. Once bias or potential bias is detected, techniques may be applied to indicate and/or compensate for the bias. Such techniques may allow users to more easily assess the veracity of search results, and increase the chances that users will locate accurate answers to their questions.

Abstract: Various technologies pertaining to exploratory suggestions are described herein. A computer-implemented graph is constructed, where the graph includes nodes that are representative of aspects and edges that are representative of associations between aspects. An aspect is representative of a sub-topic of a topic or a sub-task of a task. The computer-implemented graph is learned based upon content of search logs, and is used to output exploratory suggestions, where a user is exploring a topic or attempting to complete a multi-step task.

Abstract: Described herein are technologies pertaining to determining which search engine results page (SERP), from a plurality of SERPs, is preferable to a user. A query is received, and multiple SERPS are retrieved based upon the query, wherein the multiple SERPs are generated independently from one another. Values of features of the query and the multiple SERPs are obtained, and a determination as to which of the SERPs from the multiple SERPs is preferable to the user is made based upon the values of the features. The SERP determined to be preferable over other SERPs in the multiple SERPs is presented to the user.