At&t Intellectual Property I, LP

Nuance Communications, Inc.

Linkedin Corporation

Suhrid Balakrishnan

Sumit Chopra

David Lee Applegate

Simon Urbanek

Jason D Williams

Suhas Mathur

Baris Coskun

Lihong Li

Srinivas Bangalore

Piotr Mirowski

Jason William

A system that incorporates teachings of the subject disclosure may include, for example, determining identified impressions that are detected from consumption data collected from a group of media processors where the identified impressions represent viewing of selected content and where the consumption data indicates channel tuning events at the group of media processors including changing of channels, applying a ridge regression analysis to the identified impressions to determine a predicted number of target impressions per advertisement slot, and generating a media plan based on a ratio of an advertisement slot cost to the predicted number of target impressions per advertisement slot. Other embodiments are disclosed.

Method and apparatus for managing advertising

Methods, apparatus, systems and articles of manufacture are disclosed to identify candidate boundaries of Internet protocol addresses associated with a malicious Internet protocol address. An example method includes collecting, with a processor, netflow data associated with the Internet protocol addresses within a netblock having a lower boundary Internet protocol address and an upper boundary Internet protocol address, generating, with the processor, a first window of Internet protocol addresses numerically lower than the malicious Internet protocol address, generating, with the processor, a second window of Internet protocol addresses numerically higher than the malicious Internet protocol address, for respective Internet protocol addresses in the first and second windows, calculating, with the processor, occurrence counts associated with behavior features, and identifying candidate boundaries within the netblock based on divergence values caused by the behavior features.

Methods and apparatus to identify an internet protocol address blacklist boundary

Disclosed herein are systems, methods, and computer-readable storage media for estimating reliability of alternate speech recognition hypotheses. A system configured to practice the method receives an N-best list of speech recognition hypotheses and features describing the N-best list, determines a first probability of correctness for each hypothesis in the N-best list based on the received features, determines a second probability that the N-best list does not contain a correct hypothesis, and uses the first probability and the second probability in a spoken dialog. The features can describe properties of at least one of a lattice, a word confusion network, and a garbage model. In one aspect, the N-best lists are not reordered according to reranking scores. The determination of the first probability of correctness can include a first stage of training a probabilistic model and a second stage of distributing mass over items in a tail of the N-best list.

System and method for estimating the reliability of alternate speech recognition hypotheses in real time

Methods, systems, and products adapt recommender systems with pairwise feedback. A pairwise question is posed to a user. A response is received that selects a preference for a pair of items in the pairwise question. A latent factor model is adapted to incorporate the response, and an item is recommended to the user based on the response.

Adaptive pairwise preferences in recommenders

Disclosed herein are systems, methods, and non-transitory computer-readable storage media for predicting probabilities of words for a language model. An exemplary system configured to practice the method receives a sequence of words and external data associated with the sequence of words and maps the sequence of words to an X-dimensional vector, corresponding to a vocabulary size. Then the system processes each X-dimensional vector, based on the external data, to generate respective Y-dimensional vectors, wherein each Y-dimensional vector represents a dense continuous space, and outputs at least one next word predicted to follow the sequence of words based on the respective Y-dimensional vectors. The X-dimensional vector, which is a binary sparse representation, can be higher dimensional than the Y-dimensional vector, which is a dense continuous space. The external data can include part-of-speech tags, topic information, word similarity, word relationships, a particular topic, and succeeding parts of speech in a given history.

System and method for feature-rich continuous space language models

Methods, apparatus, systems and articles of manufacture are disclosed to identify an Internet protocol address blacklist boundary. An example method includes identifying a netblock associated with a malicious Internet protocol address, the netblock having a lower boundary and an upper boundary, collecting netflow data associated with a plurality of Internet protocol addresses in the netblock, establishing a first window associated with a lower portion of Internet protocol addresses numerically lower than a candidate Internet protocol address, establishing a second window associated with an upper portion of Internet protocol addresses numerically higher than a candidate Internet protocol address, calculating a breakpoint score based on a comparison between a behavioral profile of the first window and a behavioral profile of the second window, and identifying a first sub-netblock when the breakpoint score exceeds a threshold value.

Disclosed herein are systems, methods, and computer-readable storage media for automatically generating a dialog manager for use in a spoken dialog system. A system practicing the method receives a set of user interactions having features, identifies an initial policy, evaluates all of the features in a linear evaluation step of the algorithm to identify a set of most important features, performs a cubic policy improvement step on the identified set of most important features, repeats the previous two steps one or more times, and generates a dialog manager for use in a spoken dialog system based on the resulting policy and/or set of most important features. Evaluating all of the features can include estimating a weight for each feature which indicates how much each feature contributes to at least one of the identified policies. The system can ignore features not in the set of most important features.

Growing community of inventors

Scotch Plains, NJ, United States of America

Suhrid Balakrishnan