Apparatus and methods of aggregating content are disclosed. A data storage device includes a host interface, a controller coupled to the host interface, and a memory array coupled to the controller. The host interface is configured to enable the data storage device to be operatively coupled to the host device. First content includes a reference to a source of second content to be embedded in the first content. The first content is retrievable via access to a resource. Upon retrieval, the reference is replaced by the second content such that the second content is embedded in the first content. The controller is configured to receive data of the resource, such received data including the second content embedded in the first content. The controller is also configured to store the received data at the memory array and, when the data storage device is operatively coupled to the host device, provide the second content embedded in the first content to the host device in response to receiving a request for the first content.

System and method of embedding second content in first content

There is provided an information processing device including a display section configured to display a first object in a virtual three-dimensional space having a depth direction of a display screen, an operation section configured to acquire an operation for moving the first object in at least the depth direction, and a controller configured to move the first object on the display screen in accordance with the acquired operation, to execute, when a region of the first object overlaps a first overlap determination region, a first process to one or both of the first and second objects, and to execute, when the region of the first object overlaps a second overlap determination region, a second process to one or both of the first and second objects. The first overlap determination region may be a region obtained by extending the second overlap determination region in at least the depth direction.

Information processing device, information processing method, and program

A social network targets advertisements to its members using inferential ad targeting An inferential ad enables advertisers to reach members that do not meet targeting criteria for lack of information A member's connections in the social network that satisfy the targeting criteria are leveraged to infer a targeted interest An inferential ad is selected from a candidate set to be presented to the member Varying complexities of targeting criteria, secondary inferential targeting criteria, and scopes of inference provide flexibility for inferential ad targeting in a social network

Leveraging Information in a Social Network for Inferential Targeting of Advertisements

Click-through rate (CTR) prediction has been one of the most central problems in computational advertising. Lately, embedding techniques that produce low-dimensional representations of ad IDs drastically improve CTR prediction accuracies. However, such learning techniques are data demanding and work poorly on new ads with little logging data, which is known as the cold-start problem. In this paper, we aim to improve CTR predictions during both the cold-start phase and the warm-up phase when a new ad is added to the candidate pool. We propose Meta-Embedding, a meta-learning-based approach that learns to generate desirable initial embeddings for new ad IDs. The proposed method trains an embedding generator for new ad IDs by making use of previously learned ads through gradient-based meta-learning. In other words, our method learns how to learn better embeddings. When a new ad comes, the trained generator initializes the embedding of its ID by feeding its contents and attributes. Next, the generated embedding can speed up the model fitting during the warm-up phase when a few labeled examples are available, compared to the existing initialization methods. Experimental results on three real-world datasets showed that Meta-Embedding can significantly improve both the cold-start and warm-up performances for six existing CTR prediction models, ranging from lightweight models such as Factorization Machines to complicated deep models such as PNN and DeepFM. All of the above apply to conversion rate (CVR) predictions as well.

Warm Up Cold-start Advertisements: Improving CTR Predictions via Learning to Learn ID Embeddings

Methods, systems and apparatus, including computer program products, for expanding search queries. One method includes receiving a search query, selecting a synonym of a term in the search query based on a context of occurrence of the term in the received search query, the synonym having been derived from statistical machine translation of the term, and expanding the received search query with the synonym and using the expanded search query to search a collection of documents. Alternatively, another method includes receiving a request to search a corpus of documents, the request specifying a search query, using statistical machine translation to translate the specified search query into an expanded search query, the specified search query and the expanded search query being in the same natural language, and in response to the request, using the expanded search query to search a collection of documents.

Machine translation for query expansion

Advertisements are selected for display on search results pages or web pages displaying requested content. A request associated with a user is received for an advertisement, such as for display on a search results page or a content-displaying web page. Profile information associated with the user is identified. An inverted index is queried based on the identified profile information. The inverted index includes a list of user attributes and a list of at least one advertisement and corresponding weight factor that correspond to each listed user attribute. A plurality of advertisements is determined in the inverted index based on the query. The determined advertisements are filtered to generate an advertisement presentation configuration that includes at least one of the identified advertisements.

Advertisement selection for internet search and content pages

Content recommendations customized to a user's knowledge are provided. The user's knowledge is assessed from the user's activity history and the expertise of the user regarding each of the various topics relative to a cohort group is determined. Based on the user's score, the user can be classified into various competency levels ranging from a novice to an expert in each topic. Content items for improving the user's scores in the various topics can be forwarded based on the user's classification and activity history. If the user is recognized as an expert in a particular topic, questions from other users regarding the particular topic can be directed to the user for the responses.

Relative expertise scores and recommendations

News search and browse experience is personalized based on user preferences. User attributes like a geographic location are obtained and news sources preferred by other users with attributes similar to those of a requesting user are identified. News sources that are popular across different user groups are eliminated and relevant news items from the remaining news sources are retrieved and presented to the requesting user.

Personalization of news articles based on news sources

In this paper, we describe an exploration system that was implemented by the search-advertising team of a prominent web-portal to address the cold ads problem. The cold ads problem refers to the situation where, when new ads are injected into the system by advertisers, the system is unable to assign an accurate quality to the ad (in our case, the click probability). As a consequence, the advertiser may suffer from low impression volumes for these cold ads, and the overall system may perform sub-optimally if the click probabilities for new ads are not learnt rapidly. We designed a new exploration system that was adapted to search advertising and the serving constraints of the system. In this paper, we define the problem, discuss the design details of the exploration system, new evaluation criteria, and present the performance metrics that were observed by us.

A Practical Exploration System for Search Advertising

A system for selecting advertisements for a web page. An advertisement request is received and the web page content is evaluated to identify a first advertisement query based on the content of the web page and a second advertisement query based on the content of the web page or a behavioral feature. A first set of advertisements is retrieved based on the first advertisement query and a second set of advertisements is retrieved based on the second advertisement query. The first set of advertisements is blended with the second set of advertisements to form a blended advertisement set. The blended advertisement set is provided for display with the web page.

Ben Shahshahani

Papers

Advertisement selection for internet search and content pages

Relative expertise scores and recommendations

Personalization of news articles based on news sources

A Practical Exploration System for Search Advertising

Diversity of ads displayed on a publisher page