Microsoft Technology Licensing, LLC

Alcatel Lucent

Christopher J Burges

John Carlton Platt

Christopher Bruce Weare

Alice Zheng

Steven E Swenson

Eric David Brill

Yevgeny E Agichtein

Craig R Nohl

Jan I Ben

Steven E Swnson

Madjid Sam Mousavi

Steven Mark Drucker

Ryen William White

Robert J Ragno

Dengyong Zhou

Tao Tao

Irina Matveeva

Andrew Samuel Laucius

Leon C W Wong

Timo Burkard

The content of a media program is recognized by analyzing its audio content to extract therefrom prescribed features, which are compared to a database of features associated with identified content. The identity of the content within the database that has features that most closely match the features of the media program being played is supplied as the identity of the program being played. The features are extracted from a frequency domain version of the media program by a) filtering the coefficients to reduce their number, e.g., using triangular filters; b) grouping a number of consecutive outputs of triangular filters into segments; and c) selecting those segments that meet prescribed criteria, such as those segments that have the largest minimum segment energy with prescribed constraints that prevent the segments from being too close to each other. The triangular filters may be log-spaced and their output may be normalized.

Content identification system

A spam detection system is disclosed. The system includes a classifier training component that receives a first set of training pages labeled as normal pages and a second set of training pages labeled as spam pages. The training component trains a web page classifier based on both the first set of training pages and the second set of training pages. A spam detector then receives unlabeled web pages uses the web page classifier to classify the unlabeled web pages as spam pages or normal pages.

Link spam detection using smooth classification function

Structured content and associated metadata from the Web are leveraged to provide specific answer string responses to user questions. The structured content can also be indexed at crawl-time to facilitate searching of the content at search-time. Ranking techniques can also be employed to facilitate in providing an optimum answer string and/or a top K list of answer strings for a query. Ranking can be based on trainable algorithms that utilize feature vectors for candidate answer strings. In one instance, at crawl-time, structured content is indexed and automatically associated with metadata relating to the structured content and the source web page. At search-time, candidate indexed structured content is then utilized to extract an appropriate answer string in response to a user query.

Question answering over structured content on the web

The concept of variability pertains to whether users exhibit consistent search interaction patterns, for example, in terms of interaction flow or information targeted. Methods are provided for analyzing variability, and then adapting search-related functionality (e.g., processes and/or interfaces) to account for variability characteristics, for example, to account for predictable search interaction behavior.

Accounting for behavioral variability in web search

A unique system and method that facilitates improving the ranking of items is provided. The system and method involve re-ranking decreasing subsets of high ranked items in separate stages. In particular, a basic ranking component can rank a set of items. A subset of the top or high ranking items can be taken and used as a new training set to train a component for improving the ranking among these high ranked documents. This process can be repeated on an arbitrary number of successive high ranked subsets. Thus, high ranked items can be reordered in separate stages by focusing on the higher ranked items to facilitate placing the most relevant items at the top of a search results list.

Ranking results using multiple nested ranking

The subject disclosure pertains to systems and methods for facilitating training of machine learning systems utilizing pairwise training. The number of computations required during pairwise training is reduced by grouping the computations. First, a score is generated for each retrieved data item. During processing of the data item pairs, the scores of the data items in the pair are retrieved and used to generate a gradient for each data item. Once all of the pairs have been processed, the gradients for each data item are aggregated and the aggregated gradients are used to update the machine learning system.

Efficiency of training for ranking systems based on pairwise training with aggregated gradients

A system and method for generating a list is provided. The system includes a seed item input subsystem, an item identifying subsystem, a descriptive metadata similarity determining subsystem and a list generating subsystem that builds a list based, at least in part, on similarity processing performed on seed item descriptive metadata and user item descriptive metadata and user selected thresholds applied to such similarity processing. The method includes inexact matching between identifying metadata associated with new user items and identifying metadata stored in a reference metadata database. The method further includes subjecting candidate user items to similarity processing, where the degree to which the candidate user items are similar to the seed item is determined, and placing user items in a list of items based on user selected preferences for (dis)similarity between items in the list and the seed item.

Auto playlist generator

The subject disclosure pertains to systems and methods for training machine learning systems. Many cost functions are not smooth or differentiable and cannot easily be used during training of a machine learning system. The machine learning system can include a set of estimated gradients based at least in part upon the ranked or sorted results generated by the learning system. The estimated gradients can be selected to reflect the requirements of a cost function and utilized instead of the cost function to determine or modify the parameters of the learning system during training of the learning system.

Growing community of inventors

Bellevue, WA, United States of America

Christopher J Burges