Abstract: Systems and methods for recommending content to an online service subscriber are presented. For each subscriber, content items that were the subject of the subscriber's prior interactions are projected, via associated embedding vectors, into a content item embedding space. The content items, via their projections into the content item embedding space, are clustered to form a plurality of interest clusters for the subscriber. A representative embedding vector is determined for each interest cluster, and a plurality of these embedding vectors are stored as the representative embedding vectors for the subscriber. The online service, in response to a request for recommended content for a subscriber, selects a first representative embedding vector associated with the subscriber and identifies a new content item from a corpus of content items according to a similarity measure between the first representative embedding vector and an embedding vector associated with the new content item.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for providing content. One of the methods includes providing a plurality of image content items to an application interface of a client device for presentation; receiving a user selection of a particular image content item of the plurality of presented image content items; and responsive to the selection, providing a combination of native content and third party content associated with the selected image content item, wherein the native content includes a close up view of the selected image content item and the third party content includes a third party webpage.

Abstract: This application describes a system and process for providing object identifiers relating to real world objects to users based on the location of the user and the anticipated interested of the user in an object within a defined distance of the user. For example, if the user is within a retail store, a portable device associated with the user may detect or receive a beacon transmitted from a location within the retail store and object identifiers representative of objects within the store may be generated and provided to the user. In some implementations, only object identifier representative of items determined to be of likely interest to the user may be provided for presentation to the user.

Abstract: The described implementations facilitate the discovery and presentation of video advertisements in a non-intrusive manner by users of client devices. In one implementation, an informed opt-in preview representative of a video advertisement is generated. The informed opt-in preview is a short video presentation that is formed from frames extracted from the video advertisement that can be presented on a client device to provide a user with an overview of the video advertisement corresponding to that informed opt-in preview. For example, the video advertisement may be a two-minute video advertisement. In comparison, the informed opt-in preview may be as little as three—five seconds in length and simply provide an overview of the video advertisement.

Abstract: Disclosed are implementations that enable the linking or connection of objects and different scenes in which those objects are represented. For example, a corpus of scenes (e.g., digital images) that include a representation of one or more objects may be processed using the disclosed implementations to segment from those scenes the individual objects represented in those scenes. The disclosed implementations may further determine clusters of visually similar object segments and form object clusters for those object segments. The scenes that include those object segments are also linked to the object cluster. With scenes linked to different object clusters, a user may select one or more query objects or a query scene and be presented with other scenes that include visually similar objects, even though the overall scenes may be visually different.

Abstract: According to aspects of the disclosed subject matter, a taste graph comprising likely content collection nodes with corresponding likely digital content items is generated through one or more analyses of a corpus of content collections that is maintained by the online content service. As should be understood, this corpus of content collections is comprised of a plurality of curated content collections, with each content collection comprising a plurality of digital content items. With this taste graph available, as a user generates (or in response to a user generating) a content collection of digital content items, reference can be made to the taste graph to identify one or more digital content items that may be added to the content collection, where the one or more digital content items have a probabilistic likelihood of being complimentary and/or compatible with the other digital content items of the content collection.

Abstract: A system for visual discovery is disclosed. The system identifies a visual search query in response to an action associated with an image presented to a user of a client device. The system extracts visual features from the visual search query and compares the visual features with visual features of stored content items. The system then identifies a set of candidate visual content items from the stored content items that have visual features, which are similar to the visual features of the visual search query. The candidate visual content items are ranked using information from a user session and provided for display to the user.

Abstract: A system for and a method of using user-entered information to return more meaningful information in response to Internet search queries are disclosed. A method in accordance with the disclosed subject matter comprises managing a database in response to multiple user inputs and displaying search results from the database in response to a search query. The search results include a results list and supplemental data related to the search query. Managing the database includes, among other things, re-ranking elements in the results list, storing information related to relevancies of elements in the results list, blocking a link in the results list, storing links to documents related to the search query, or any combination of these. The supplemental data include descriptions of or indices to one or more concepts related to the search query.

Abstract: An online host for conducting a promotion campaign is presented. Online behaviors of subscribers exposed by the promotion campaign are tracked for determining conversion counts for the promotion campaign. For exposed subscribers whose online behaviors are not sufficiently available to the online host to determine conversion counts (non-measurable subscribers), a machine learning model is trained to predict conversion counts based on online behaviors that are conducted on internet locations under control of the online service, and further trained to determine an estimated error rate regarding the predicted conversion counts.

Abstract: Systems and methods are set forth for identifying key-words and key-phrases, collectively referred to as key-terms, from a document. A document is accessed and the document is tokenized, each token corresponding to a word or phrase occurring within the document. Term frequencies of the terms of the tokens may be determined and TF-IDF scores may be generated according to the term frequencies. Embedding vectors for the terms of the tokens may be generated and a document embedding vector may be generated according to the embedding vectors of the documents. A similarity score may be determined for each token according to the embedding vector of a token and the document embedding vector. Additionally, an overall score may be determined for each token according to the term of the token, a TF-IDF score, similarity scores, and the like. Terms from the highest scoring tokens are selected as the key-terms for the document.

Abstract: Described is a system and method for enabling visual search for information. With each selection of a search term, additional search terms are dynamically selected and presented to the user in conjunction with results matching the currently selected search terms. Likewise, a selected search term may be tokenized and a graphical token presented to the user to represent the selected search term.

Abstract: This disclosure describes systems and methods that facilitate reducing a data set that may be used to construct a node graph. For example, the data set may include collections, representations, and associations between the collections and the representations. Topic scores may be determined for the representations, and diversity scores for each collection may be determined based on the topic scores of representations that are associated with the respective collection. If the diversity score is too high, then the collection and its associations are excluded from being incorporated into a node graph that is subsequently constructed from the data set. Topic scores may also be determined for collections in the data set based on the topic scores of representations that are associated with each collection.

Abstract: Techniques described herein are directed to generating and presenting customized directives for facilitating interactions between user(s) and user interface(s) associated with a content service provider. In an example, the content service provider may determine a state associated with a user based on user data associated with the user. Additionally, the content service provider may receive context data identifying an action performed by the user in association with content item(s) presented via a graphical user interface (GUI) and may determine an intent of the user based at least partly on the context data. Based at least partly on the state associated with the user and the intent of the user, the content service provider may determine a directive for prompting the user to access and/or use a feature associated with the content service provider and may cause a change to the GUI to communicate the directive.

Abstract: Systems and methods for recommending content to an online service user are presented. In response to a request from a user, a set of n-grams of the request are generated, with each n-gram comprising one or more terms from the request and each n-gram of the set of n-grams being unique. Embedding vectors projecting the n-grams into a content item embedding space are generated, and the embedding vectors are combined into a representative embedding vector for the request. The nearest content items are identified according to a distance measure between a projection of the representative embedding vector and embedding vectors of content items of a corpus of content items in the content item embedding space. At least some of the nearest content items are returned as recommended content in response to the request from the user.

Abstract: Systems and method for determining a topic cohesion measurement between a content item and a hyperlinked landing page are presented. In one embodiment, a plurality of content item signals is generated for the content item and a corresponding plurality of signals are generated for the hyperlinked landing page. An analysis of the corresponding signals is conducted to determine a measurement of topic cohesion, a topic cohesion score, between the content item and the hyperlinked landing page. A cohesion predictor model is trained to generate the predictive topic cohesion score between an input content item and a hyperlinked landing page. Upon a determination that the topic cohesion score is less than a predetermined threshold, remedial actions are taken regarding the hyperlink of the content item. Alternatively, positive actions may be carried out, including promoting the content item to others, associating advertisements with the content item, and the like.

Abstract: The described implementations are operable to determine potential objects of interest to a user based on a blend of the user's long-term behavior and short-term interests. Long term user behavior may be determined for the user over a period of time and represented as continuous data. Short-term interest may be determined based on objects with which the user has recently interacted and attributes of those objects may be represented together as continuous data corresponding to the short-term user interest. The continuous data of the short-term interest and long-term user behavior may be blended to produce a user embedding. The user embedding may then be compared with objects to determine objects that are of potential interest to the user.

Abstract: Described are systems and methods for establishing and generating collections of sets that contain object identifiers based on user provided annotations for the object identifiers. A set may include one or more object identifiers and each object identifier may include one or more user provided annotations. Annotations from all object identifiers within a set are processed to form a set profile signature representative of the set. The set profile signatures are then compared between different sets to identify similar sets. Similar sets are included in a collection. Utilizing set profile signatures for a set formed based on user provided annotations provides useful relationships between sets that might otherwise not exist.

Abstract: Systems and methods for identifying a selected set of users of a social networking service which, upon issuing a notice regarding a re-post activity of an item of content, will likely result in heightened user interaction with the service. Upon receiving a notice of a re-post action by a first user, the social networking service identifies a first set of users of the service that have posted that item of content. Scores are associated with the users of the first set of users, the scores indicating a likelihood of a user that, if notified of the re-post action of the first user, will result in heightened user interaction with the social networking service. A subset of users of the first set of users are identified according to their associated scores and a notice of the re-post action by the first user is sent to the users of this subset of users.

Abstract: The described implementations are operable to determine potential objects of interest to a user based on a blend of the user's long-term behavior and short-term interests. Long term user behavior may be determined for the user over a period of time and represented as continuous data. Short-term interest may be determined based on objects with which the user has recently interacted and attributes of those objects may be represented together as continuous data corresponding to the short-term user interest. The continuous data of the short-term interest and long-term user behavior may be blended to produce a user embedding. The user embedding may then be compared with objects to determine objects that are of potential interest to the user.

Abstract: Systems and methods are presented for efficient and effective computation of LSH hashing functions for use in various environments, including nearest-neighbor search. A corpus of items is maintained, with each item of the corpus being associated with information identifying one of a plurality of LSH partitions to which the item has been mapped or hashed. In response to an input item, the input item is projected one or more times into an orthoplex inscribed within a multi-dimensional space. For each mapping, a determination is made as to the nearest vertex of the orthoplex to the projected input item in view of determined offsets that provide for balanced distribution, and the LSH partitions associated with the nearest vertex are aggregated and associated with the input item as the input item's LSH partition.