Abstract: In an example embodiment, one or more specified ideal candidates are used to perform a search in a database. One or more attributes are extracted from one or more ideal candidate member profiles. A search query is then generated based on the extracted one or more attributes. Then, a search is performed on member profiles in the social networking service using the generated search query, returning one or more result member profiles.

Abstract: In an example embodiment, one or more query terms are obtained. Then, for each of the one or more query terms, a standardized entity taxonomy is searched to locate a standardized entity that most closely matches the query term, with the standardized entity taxonomy comprising an entity identification for each of a plurality of different standardized entities. A confidence score is then calculated for the query term-standardized entity pair for the standardized entity that most closely matches the query term, and the query term is tagged with the entity identification corresponding to the standardized entity that most closely matches the query term and the calculated confidence score.

Abstract: A system and method for generating modifiers for updated search queries are provided. In example embodiments, metadata is accessed, the metadata corresponds to search results of an input query and comprising a plurality of candidate modifiers. A score is calculated for each candidate based on a relevance value that indicates the correlation between a candidate modifier and the input query. A list of top number of candidate modifiers is generated based on the score of the candidate modifier transgressing a first threshold. A uniqueness score is calculated for combination pairs of candidate modifiers within the list, the uniqueness score being used to eliminate candidate modifiers. The list of top number of candidate modifiers is presented, at a user interface, according to a ranked order based on the score.

Abstract: In an example embodiment, one or more sample ideal candidate member profiles in a social networking service are obtained, as well as one or more sample search result member profiles in the social networking service. Then, for each unique pair of sample ideal candidate member profile and sample search result member profile, a label is generated using a score generated from log information of the social networking service, the log information including records of communications between a searcher and members of the social networking service, the score being higher if the searcher communicated with both the member corresponding sample ideal candidate member profile and the member corresponding to the sample search result member profile in a same search session. The generated labels are fed into a machine learning algorithm to train a combined ranking model used to output ranking scores for search result member profiles.

Abstract: System and techniques for facet expansion are described herein. A user interface element may be presented on facet selection portion of a search result display including search results. Here, the user interface element is arranged to accept user input of a facet. Partial user input for a facet may be received. A peer entity to an entity corresponding to the facet may be obtained. A peer facet may be presented in a suggestion element in the facet selection portion in response to receiving the partial user input.

Abstract: In an example embodiment, a query for search results is received, the query including at least one value for one facet, a facet defining a categorical dimension for the search results. It is then determined that the facet in the query is exclusive. In response to the determination that the facet is exclusive: for each potential facet different from the facet in the query: for each potential value in the potential facet: conditional entropy gain of the value in the query and the potential value is determined. The potential value in the potential facet that has the highest conditional entropy gain is determined, as is the potential facet with the minimum maximum conditional entropy gain. Then the potential facet with the minimum maximum is input into a machine learning model, causing the machine learning model to output one or more suggested facets to add to the query.

Abstract: In an example embodiment, one or more query terms are obtained. Then, for each of the one or more query terms, a standardized entity taxonomy is searched to locate a standardized entity that most closely matches the query term, with the standardized entity taxonomy comprising an entity identification for each of a plurality of different standardized entities. A confidence score is then calculated for the query term-standardized entity pair for the standardized entity that most closely matches the query term, and the query term is tagged with the entity identification corresponding to the standardized entity that most closely matches the query term and the calculated confidence score.

Abstract: In an example embodiment, one or more query terms are obtained. Then, for each of the one or more query terms, a standardized entity taxonomy is searched to locate a standardized entity that most closely matches the query term, with the standardized entity taxonomy comprising an entity identification for each of a plurality of different standardized entities. A confidence score is then calculated for the query term-standardized entity pair for the standardized entity that most closely matches the query term, and the query term is tagged with the entity identification corresponding to the standardized entity that most closely matches the query term and the calculated confidence score.

Abstract: A system and method for generating modifiers for updated search queries are provided. In example embodiments, metadata is accessed, the metadata corresponds to search results of an input query and comprising a plurality of candidate modifiers. A score is calculated for each candidate based on a relevance value that indicates the correlation between a candidate modifier and the input query. A list of top number of candidate modifiers is generated based on the score of the candidate modifier transgressing a first threshold. A uniqueness score is calculated for combination pairs of candidate modifiers within the list, the uniqueness score being used to eliminate candidate modifiers. The list of top number of candidate modifiers is presented, at a user interface, according to a ranked order based on the score.

Abstract: In an example embodiment, a query for search results is received, the query including at least one value for one facet, a facet defining a categorical dimension for the search results. It is then determined that the facet in the query is exclusive. In response to the determination that the facet is exclusive: for each potential facet different from the facet in the query: for each potential value in the potential facet: conditional entropy gain of the value in the query and the potential value is determined. The potential value in the potential facet that has the highest conditional entropy gain is determined, as is the potential facet with the minimum maximum conditional entropy gain. Then the potential facet with the minimum maximum is input into a machine learning model, causing the machine learning model to output one or more suggested facets to add to the query.

Abstract: In an example embodiment, one or more ideal candidate member profiles in a social networking service are obtained. Then a search is performed on member profiles in the social networking service using a search query, returning one or more result member profiles. One or more query-based features are produced from the one or more result member profiles using the search query. One or more ideal candidate-based features are produced from the one or more result member profiles using the one or more ideal candidate member profiles. The one or more query-based features and the one or more ideal candidate-based features are input to a combined ranking model trained by a machine learning algorithm to output a ranking score for each of the one or more result member profiles. The one or more result member profiles are then ranked based on the ranking scores.

Abstract: In an example embodiment, one or more specified ideal candidates are used to perform a search in a database. One or more attributes are extracted from one or more ideal candidate member profiles. A search query is then generated based on the extracted one or more attributes. Then, a search is performed on member profiles in the social networking service using the generated search query, returning one or more result member profiles.

Abstract: In an example embodiment, one or more sample ideal candidate member profiles in a social networking service are obtained, as well as one or more sample search result member profiles in the social networking service. Then, for each unique pair of sample ideal candidate member profile and sample search result member profile, a label is generated using a score generated from log information of the social networking service, the log information including records of communications between a searcher and members of the social networking service, the score being higher if the searcher communicated with both the member corresponding sample ideal candidate member profile and the member corresponding to the sample search result member profile in a same search session. The generated labels are fed into a machine learning algorithm to train a combined ranking model used to output ranking scores for search result member profiles.

Abstract: In an example embodiment, as time goes on and as refinements are received to an online search, weights assigned to each of the one or more query-based features are dynamically trained to increase as more refinements are received and weights assigned to each of the one or more ideal candidate-based features to decrease as more refinements are received.

Abstract: In an example embodiment, one or more query terms are obtained. Then, for each of the one or more query terms, a standardized entity taxonomy is searched to locate a standardized entity that most closely matches the query term, with the standardized entity taxonomy comprising an entity identification for each of a plurality of different standardized entities. A confidence score is then calculated for the query term-standardized entity pair for the standardized entity that most closely matches the query term, and the query term is tagged with the entity identification corresponding to the standardized entity that most closely matches the query term and the calculated confidence score.

Abstract: System and techniques for autonomously adaptive performance monitoring are described herein. A text input field may be presented on a graphical user interface. A flow-selector may be presented in contact with the text input field in response to receiving user input at the text input field. Here, the flow-selector includes a set of flow choices selected based on the user input. A user selection of a flow choice may be received. Next-steps flow elements may be presented in response to the user selection. User query choices may be collected from the next-steps flow elements to populate a query template corresponding to the flow choice. The query template is executed to produce search results.

Abstract: System and techniques for facet expansion are described herein. A user interface element may be presented on facet selection portion of a search result display including search results. Here, the user interface element is arranged to accept user input of a facet. Partial user input for a facet may be received. A peer entity to an entity corresponding to the facet may be obtained. A peer facet may be presented in a suggestion element in the facet selection portion in response to receiving the partial user input.

Abstract: Techniques for optimizing non-convex function for learning to rank are described. Consistent with some embodiments, a search module may set an order for a group of search features. The group of search features can be used by a ranking model to determine the relevance of items in a search query. Additionally, the search module can assign a first weight factor to a first search feature in the group of search features. Moreover, the search module can calculate a mean reciprocal rank for the search query based on the assigned first weight factor. Furthermore, the search module can determine a second weight factor, using a preset incremental vector, for a second search feature in the group of search features to maximize the mean reciprocal rank for the search query. Subsequently, the search module can assign the second weight factor to the second search feature in the group of search features.

Abstract: A web search system uses humans to rank the relevance of results returned for various sample search queries. The search results may be divided into groups allowing training and validation with the ranked results. Consistent guidelines for human evaluation allow consistent results across a number of people performing the ranking. After a machine learning categorization tool, such as MART, has been programmed and validated, it may be used to provide an absolute rank of relevance for documents returned, rather than a simple relative ranking, based, for example, on key word matches and click counts. Documents with lower relevance rankings may be excluded from consideration when developing related refinements, such as category and price sorting.

Abstract: Outlier images—those images that differ substantially from other images in a set—can be automatically identified. One or more penalty values can be assigned to each image that quantifies how different that image is from others in the set. A threshold can be determined based on the set of penalty values. Each image whose penalty values are above the threshold is an outlier image. The penalty values can be the sum of per-pixel penalty values multiplied by the number of pixels with nonzero penalty values. A per-pixel penalty value can be the difference between a color value for that pixel and a predetermined range of color values, based on corresponding pixels in other images. The per-pixel penalty value can be determined for each component color and then optionally summed together. The threshold penalty values can be adjusted to provide for greater, or less, sensitivity to differences among the images.