Abstract: Techniques of providing category recommendations include a category recommendation system that provides users recommended categories based on implicit data (e.g., user-item interactions) and/or explicit data (e.g., queries, user information). The recommendations can be personalized or non-personalized (i.e., depending if user embeddings are used), queried or non-queried (i.e., depending on whether query embeddings are used), or personalized and queried (if both user and query embeddings are used). In any of these cases, there is an offline mode and a serving mode. In the offline mode, a category embedding is generated from an aggregation of item embeddings associated with a candidate category. In the serving mode, the candidate category is selected for display on a user device based on a similarity between the category embedding and either, or both, of the user embedding and the query embedding.

Abstract: Methods and apparatus for generating, in response to a search query of a user, a personal search result that identifies a physical location previously interacted with by the user, such as a physical location previously visited by the user. Some implementations are directed to methods and apparatus for determining whether a search query is a personal locational query indicating a desire for information related to one or more physical locations previously interacted with by the user. Some implementations are directed to methods and apparatus for determining search parameters for such a personal locational query. Some implementations are directed to methods and apparatus for searching private content of the user to determine physical locations previously interacted with by the user that are responsive to such a personal locational query.

Abstract: Methods and apparatus for generating, in response to a search query of a user, a personal search result that identifies a physical location previously interacted with by the user, such as a physical location previously visited by the user. Some implementations are directed to methods and apparatus for determining whether a search query is a personal locational query indicating a desire for information related to one or more physical locations previously interacted with by the user. Some implementations are directed to methods and apparatus for determining search parameters for such a personal locational query. Some implementations are directed to methods and apparatus for searching private content of the user to determine physical locations previously interacted with by the user that are responsive to such a personal locational query.

Abstract: Methods and apparatus for generating, in response to a search query of a user, a personal search result that identifies a physical location previously interacted with by the user, such as a physical location previously visited by the user. Some implementations are directed to methods and apparatus for determining whether a search query is a personal locational query indicating a desire for information related to one or more physical locations previously interacted with by the user. Some implementations are directed to methods and apparatus for determining search parameters for such a personal locational query. Some implementations are directed to methods and apparatus for searching private content of the user to determine physical locations previously interacted with by the user that are responsive to such a personal locational query.

Abstract: Implementations include systems and methods for scoring candidates for set recommendation problems. An example method includes repeating, for each code in code arrays for items in a set of items, determining a most common value for the code. In some implementations, the method includes determining that the most common value occurs with a frequency that meets an occurrence threshold and adding the code and the most common value to set-inclusion criteria. In other implementations, the method includes determining a value for the code from a code array for a seed item and adding the code and the most common value to set-inclusion criteria when the value for the code from the code array for the seed item matches the most common value. The method may also include evaluating a similarity with a candidate item based on the set-inclusion criteria and basing a recommendation regarding the candidate item on the similarity.

Abstract: Methods and apparatus for generating, in response to a search query of a user, a personal search result that identifies a physical location previously interacted with by the user, such as a physical location previously visited by the user. Some implementations are directed to methods and apparatus for determining whether a search query is a personal locational query indicating a desire for information related to one or more physical locations previously interacted with by the user. Some implementations are directed to methods and apparatus for determining search parameters for such a personal locational query. Some implementations are directed to methods and apparatus for searching private content of the user to determine physical locations previously interacted with by the user that are responsive to such a personal locational query.

Abstract: Implementations include systems and methods for scoring candidates for set recommendation problems. An example method includes repeating, for each code in code arrays for items in a set of items, determining a most common value for the code. In some implementations, the method includes determining that the most common value occurs with a frequency that meets an occurrence threshold and adding the code and the most common value to set-inclusion criteria. In other implementations, the method includes determining a value for the code from a code array for a seed item and adding the code and the most common value to set-inclusion criteria when the value for the code from the code array for the seed item matches the most common value. The method may also include evaluating a similarity with a candidate item based on the set-inclusion criteria and basing a recommendation regarding the candidate item on the similarity.

Abstract: Methods and apparatus for generating, in response to a search query of a user, a personal search result that identifies a physical location previously interacted with by the user, such as a physical location previously visited by the user. Some implementations are directed to methods and apparatus for determining whether a search query is a personal locational query indicating a desire for information related to one or more physical locations previously interacted with by the user. Some implementations are directed to methods and apparatus for determining search parameters for such a personal locational query. Some implementations are directed to methods and apparatus for searching private content of the user to determine physical locations previously interacted with by the user that are responsive to such a personal locational query.

Abstract: Techniques for using social networking information may include making a determination that content authored by a first party references a second party more than a specified number of times. An adjustment in affinity may be made between the first party and the second party in the social network in response to the determination. Making the adjustment in affinity may include modifying a social graph of at least the first party that is referenced by the social network in order to reflect the adjustment in affinity. Modifying the social graph includes creating a closer connection between the first party and the second party than had existed prior to the determination. In response to the adjustment in the affinity, promotion is adjusted, to the first party, of content in the social network that has a connection to the second party.

Abstract: Methods and apparatus for generating, in response to a search query of a user, a personal search result that identifies a physical location previously interacted with by the user, such as a physical location previously visited by the user. Some implementations are directed to methods and apparatus for determining whether a search query is a personal locational query indicating a desire for information related to one or more physical locations previously interacted with by the user. Some implementations are directed to methods and apparatus for determining search parameters for such a personal locational query. Some implementations are directed to methods and apparatus for searching private content of the user to determine physical locations previously interacted with by the user that are responsive to such a personal locational query.

Abstract: Embodiments are directed towards employing long and short term historical user click propensity behaviors to adapt or filter a number of advertisements displayed and their location on a search results' page. A network device tracks a user's short and long term historical click behaviors. For a given search query for the user, a variety of candidate advertisements are selected. A normalized click-through rate (COEC) is estimated for each advertisement. The COEC and the user's short and long term click behavior, represented by User Click Propensity (UCP), is used to generate a User effective Cost Per Thousand (UeCPM) value. Candidate advertisements are filtered based on a minimum threshold value for UeCPMs. Page placement for the remaining advertisements is determined based on a user expected revenue for an advertisement determined from the UCP. Advertisements having a user expected revenue above another threshold are placed in a north page location.

Abstract: A method for executing multiple, cascading ad auctions, including receiving a request to deliver ads in response to a search query for display on a search results page having a plurality of ad sections; executing at least first and second sequential auctions for the plurality of ad sections by: ranking the ads in the first auction and identifying which of the ads placeable in the North section to deliver according to a first utility function that considers a relevance of the search results page with the ads placed; ranking a remainder of the ads not identified for delivery to the North section in the second auction and identifying which of the remainder of the ranked ads to deliver to a second section based on a second utility function; and delivering the ads identified by the first utility function for display in the North section and the ads identified by the second utility function for display in the second section.

Abstract: A method for reducing ad impact on users in a search results page includes receiving a request to deliver ads in response to a search query for display on a search results page; receiving relevance scores for a plurality of ranked web results that are to be served to the search results page; ranking a plurality of ads identified as relevant to the search query according to a position-normalized, click-through-rate metric and bid values, wherein a predetermined number of the top-ranked ads are placeable in a plurality of North ad slots; incrementally and additively placing the placeable ads sequentially according to rank (k) in their respective North ad slots until a utility score generated by a utility function for a current iteration of ads fails to exceed a threshold value; and delivering to the search results page the ads placed in the North ad slots.

Abstract: The present invention is directed towards systems and methods for ranking and providing advertisements in a position auction. The method of the present invention comprises receiving a search query and selecting at least one keyword based upon the search query. A list containing at least one keyword based upon the search query is returned and a list comprising at least one bid corresponding to the returned list of keywords is retrieved. The search query and list comprising at least one bid are used to train an offline simulator. The offline simulator creates a model that predicts optimal scoring factors. A priority score corresponding to each bid is computed using the optimal scoring factors and used to rank the list of bids. Advertisements are then provided corresponding to a plurality of the highest ranking bids.

Abstract: Techniques are described for normalizing dynamic URLs using a hierarchical organization of a web site. Given web pages associated with a web site, an information extraction method is used to generate data structures that represent the content or structure of each of the web pages. These data structures are appended to the corresponding dynamic URLs. The modified URLs with the data structures are tokenized with the resulting tokens clustered to create a hierarchical organization. Nodes of the hierarchical organization may be merged based upon occurrence or patterns of content and structure. The merged hierarchical organization may then be pruned to remove irrelevant information and to reduce the memory footprint of the hierarchical organization. When a new dynamic URL is received, the new dynamic URL is matched to the hierarchical organization. Important parameters are taken into account and irrelevant information may be removed.

Abstract: To approximate a visual layout of a web page without rendering the page, an object tree representing elements within the page is recursively traversed to determine bounds for the width of the elements, resulting in lower bounds induced for non-leaf nodes by elements within these nodes and upper bounds induced by ancestors and siblings of nodes. For each element, the minimum required width (lower bound), the desired width were there no constraints, and the maximum available width (upper bound) based on constraints of parents are computed, and an approximate width is derived therefrom. A positioning process positions each element within its corresponding parent container by advancing a cursor according to the elements' approximate width and appropriate constraints. The element that contains the most meaningful content is determined based on the amount of weighted content of elements and their position within the page.