Microsoft Technology Licensing, LLC

Yahoo! Inc.

Match Group, LLC

Match.com, L.l.c.

Fernando David Diaz

Sihem Amer-Yahia

Donald Metzler

Ryen William White

Rosie Jones

Qi Guo

Yi Chang

Ahmed Hassan Awadallah

Zhaohui Zheng

Nicholas Eric Craswell

David Anthony Hawking

Corbin Louis Rosset

Jing Bai

Emine Yilmaz

Bhaskar Mitra

A device includes a memory that stores a prefetching model. A control module receives a content page including one or more links each associated with selectable content and collects data associated with the content page. The collected data includes at least one of first data indicative of respective relationships between each of the links and a viewport of the device and second data indicative of characteristics of the viewport. The control module further assigns, using the prefetching model, respective scores to each of the links based on the collected data, and selectively generates, based on the assigned scores, a request to prefetch the selectable content associated with at least one of the links.

Prefetching using dynamic user model to reduce latency

Disclosed are methods and apparatus for automatically determining the relevance of matches between entities. A set of one or more indicators of relevance for each of a plurality of matches may be detected, where each of the plurality of matches exists between a first entity and a different one of a plurality of entities. Each set of one or more indicators of relevance indicates a degree of two-way interest for a corresponding one of the plurality of matches, the degree of two-way interest indicating both a degree of interest of the first entity in the corresponding one of the plurality of entities and a degree of interest of the corresponding one of the plurality of entities in the first entity. A probability of relevance of each of the plurality of matches may be determined based at least in part upon a corresponding set of one or more indicators of relevance. Each of the plurality of matches may be ranked based at least in part on the corresponding probability of relevance. A ranking function may be trained based upon the probability of relevance of each of the plurality of matches. The ranking function may subsequently be applied to identify and rank matches (e.g., in the absence of indicators of relevance).

System for determining and optimizing for relevance in match-making systems

Described herein is a mechanism for utilizing a neural network to identify and rank search results. A machine learning model is trained by converting training data comprising query-document entries into query term-document entries. The query term-document entries are utilized to train the machine learning model. A set of query terms are identified. The query terms can be derived from a query history. The trained machine learning model is used to calculate document ranking scores for the query terms and the resultant scores are stored in a pre-calculated term-document index. A query to search the document index is broken down into its constituent terms and an aggregate document ranking score is calculated from a weighted sum of the document ranking scores corresponding to the individual query terms. Because the term-document index can be pre-calculated, it can be downloaded to provide deep learning search capabilities in a computationally limited environment.

Neural network for search retrieval and ranking

Various technologies described herein pertain to automatic prediction of an anticipated audience response for scripting. A sub-document unit can be received, where the sub-document unit can be part of a script. The sub-document unit, for example, can be a sentence, a paragraph, a scene, or substantially any other portion of the script. Content of the sub-document unit and a context of the sub-document unit can be analyzed to extract features of the sub-document unit. A predictive model can be employed to predict an anticipated audience response to the sub-document unit based upon the features of the sub-document unit. Moreover, the anticipated audience response to the sub-document unit predicted by the predictive model can be output.

Predicting audience response for scripting

Embodiments are directed towards generating market-specific ranking models by leveraging target market specific pairwise preference data. The pairwise preference data includes market-specific training examples, while a ranking model from another market captures the common characteristics of the resulting ranking model. In one embodiment, the ranking model is trained by applying a Tree Based Ranking Function Adaptation (TRADA) algorithm to multi-grade labeled training data, such as editorially generated training data. Then, contradictions between the TRADA generated ranking model and target-market specific pairwise preference data are identified. For each identified contradiction, new training data is generated to correct the contradiction. Then, in one embodiment, an algorithm such as TRADA is applied to the existing ranking model and the new training data to generate a new ranking model.

Cross-market model adaptation with pairwise preference data

A system and method is disclosed for determining a prediction measurement, or measure, using geo-spatial information which can be used to determine whether or not to include type of information in search results. The prediction measurement comprises a measure of the likelihood that an item of the type of information for which the prediction measure is determined will be selected, or clicked on, by a user, if the item of the type of information is included in the search result. Without limitation, one such information type is news.

System and method of geo-based prediction in search result selection

A computer implemented method, computer-readable medium and system for deciding which external corpora, such as verticals, to integrate into primary Internet search engine results in response to a query is disclosed. Offline query-related data and user feedback data is incorporated. A probabilistic estimate is formed of the relevance of the verticals to the query.

System for integrating content from external corpora into primary search engine results

In certain implementations, a system and/or method is provided for providing search results in response to a search query. In this implementation a temporal profile of the search query is built from temporal data associated with documents retrieved in response to the search query. From features of the temporal profile it may determined whether the search query would benefit from relevance feedback from a user. If there is a determination that the search query will benefit from the relevance feedback, relevance feedback is sought from the user. Search results are provided based on the relevance feedback.

Growing community of inventors

Brooklyn, NY, United States of America

Fernando David Diaz