Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for collecting web data in order to create diverse language models. A system configured to practice the method first crawls, such as via a crawler operating on a computing device, a set of documents in a network of interconnected devices according to a visitation policy, wherein the visitation policy is configured to focus on novelty regions for a current language model built from previous crawling cycles by crawling documents whose vocabulary considered likely to fill gaps in the current language model. A language model from a previous cycle can be used to guide the creation of a language model in the following cycle. The novelty regions can include documents with high perplexity values over the current language model.

Abstract: Systems and methods are provided to collect, analyze and report social media aggregated from a plurality of social media websites. Social media is retrieved from social media websites, analyzed for sentiment, and categorized by topic and user demographics. The data is then archived in a data warehouse and various interfaces are provided to query and generate reports on the archived data. In some embodiments, the system further recognizes alert conditions and sends alerts to interested users. In some embodiments, the system further recognizes situations where users can be influenced to view a company or its products in a more favorable light, and automatically posts responsive social media to one or more social media websites.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for bootstrapping a language translation system. A system configured to practice the method performs a bidirectional web crawl to identify a bilingual website. The system analyzes data on the bilingual website to make a classification decision about whether the root of the bilingual website is an entry point for the bilingual website. The bilingual site can contain pairs of parallel pages. Each pair can include a first website in a first language and a second website in a second language, and a first portion of the first web page corresponds to a second portion of the second web page. Then the system analyzes the first and second web pages to identify corresponding information pairs in the first and second languages, and extracts the corresponding information pairs from the first and second web pages for use in a language translation model.

Abstract: A system that incorporates teachings of the present disclosure may operate, for example, obtaining a number of blogs including an initial set of annotated blogs and unannotated blogs. The initial set of annotated blogs are annotated as being either relevant to a selected media program or not relevant to the selected media program. A set of features is determined associating the selected media program with the unannotated blogs and a trained classifier is generated based on the set of features. The trained classifier is applied to the blogs to identify a subset of blogs relevant to the selected media program. An analysis is performed on the selected blogs to determine a trend related to the selected media program and a graphical user interface is presented that concurrently presents the selected blogs, the trend, and the selected media program. Other embodiments are disclosed.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for collecting web data in order to create diverse language models. A system configured to practice the method first crawls, such as via a crawler operating on a computing device, a set of documents in a network of interconnected devices according to a visitation policy, wherein the visitation policy is configured to focus on novelty regions for a current language model built from previous crawling cycles by crawling documents whose vocabulary considered likely to fill gaps in the current language model. A language model from a previous cycle can be used to guide the creation of a language model in the following cycle. The novelty regions can include documents with high perplexity values over the current language model.

Abstract: An agricultural material application management system includes an automated agricultural data collection vehicle including a location sensor. The automated agricultural data collection vehicle includes a receiver that receives sensor data including crop information, a memory that stores the plurality of locations and the sensor data, and a processor that generates a mapping correlating the crop information with the plurality of locations in the agricultural area, and generates an agricultural material application recommendation for each of the plurality of locations based on the mapping. The agricultural material application management system includes an agricultural vehicle including an interface unit that interfaces with the automated agricultural data collection vehicle and receives the agricultural material application recommendations from the agricultural data collection vehicle.

Abstract: An agricultural material application management system includes an automated agricultural data collection vehicle including a location sensor. The automated agricultural data collection vehicle includes a receiver that receives sensor data including crop information, a memory that stores the plurality of locations and the sensor data, and a processor that generates a mapping correlating the crop information with the plurality of locations in the agricultural area, and generates an agricultural material application recommendation for each of the plurality of locations based on the mapping. The agricultural material application management system includes an agricultural vehicle including an interface unit that interfaces with the automated agricultural data collection vehicle and receives the agricultural material application recommendations from the agricultural data collection vehicle.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for collecting web data in order to create diverse language models. A system configured to practice the method first crawls, such as via a crawler operating on a computing device, a set of documents in a network of interconnected devices according to a visitation policy, wherein the visitation policy is configured to focus on novelty regions for a current language model built from previous crawling cycles by crawling documents whose vocabulary considered likely to fill gaps in the current language model. A language model from a previous cycle can be used to guide the creation of a language model in the following cycle. The novelty regions can include documents with high perplexity values over the current language model.

Abstract: Determining semantically equivalent text or questions using hybrid representations based on neural network learning. Weighted bag-of-words and convolutional neural networks (CNN) based distributed vector representations of questions or text may be generated to compute the semantic similarity between questions or text. Weighted bag-of-words and CNN based distributed vector representations may be jointly used to compute the semantic similarity. A pair-wise ranking loss function trains neural network. In one embodiment, the parameters of the system are trained by minimizing a pair-wise ranking loss function over a training set using stochastic gradient descent (SGD).

Abstract: A method, computer readable medium and apparatus for detecting a sentiment for a short message are disclosed. For example, the method receives the short message, and obtains an abstraction of the short message. The method then determines the sentiment of the short message based upon the abstraction.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for bootstrapping a language translation system. A system configured to practice the method performs a bidirectional web crawl to identify a bilingual website. The system analyzes data on the bilingual website to make a classification decision about whether the root of the bilingual website is an entry point for the bilingual website. The bilingual site can contain pairs of parallel pages. Each pair can include a first website in a first language and a second website in a second language, and a first portion of the first web page corresponds to a second portion of the second web page. Then the system analyzes the first and second web pages to identify corresponding information pairs in the first and second languages, and extracts the corresponding information pairs from the first and second web pages for use in a language translation model.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for collecting web data in order to create diverse language models. A system configured to practice the method first crawls, such as via a crawler operating on a computing device, a set of documents in a network of interconnected devices according to a visitation policy, wherein the visitation policy is configured to focus on novelty regions for a current language model built from previous crawling cycles by crawling documents whose vocabulary considered likely to fill gaps in the current language model. A language model from a previous cycle can be used to guide the creation of a language model in the following cycle. The novelty regions can include documents with high perplexity values over the current language model.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for bootstrapping a language translation system. A system configured to practice the method performs a bidirectional web crawl to identify a bilingual website. The system analyzes data on the bilingual website to make a classification decision about whether the root of the bilingual website is an entry point for the bilingual website. The bilingual site can contain pairs of parallel pages. Each pair can include a first website in a first language and a second website in a second language, and a first portion of the first web page corresponds to a second portion of the second web page. Then the system analyzes the first and second web pages to identify corresponding information pairs in the first and second languages, and extracts the corresponding information pairs from the first and second web pages for use in a language translation model.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for collecting web data in order to create diverse language models. A system configured to practice the method first crawls, such as via a crawler operating on a computing device, a set of documents in a network of interconnected devices according to a visitation policy, wherein the visitation policy is configured to focus on novelty regions for a current language model built from previous crawling cycles by crawling documents whose vocabulary considered likely to fill gaps in the current language model. A language model from a previous cycle can be used to guide the creation of a language model in the following cycle. The novelty regions can include documents with high perplexity values over the current language model.

Abstract: A system that incorporates teachings of the present disclosure may operate, for example, obtaining a number of blogs including an initial set of annotated blogs and unannotated blogs. The initial set of annotated blogs are annotated as being either relevant to a selected media program or not relevant to the selected media program. A set of features is determined associating the selected media program with the unannotated blogs and a trained classifier is generated based on the set of features. The trained classifier is applied to the blogs to identify a subset of blogs relevant to the selected media program. An analysis is performed on the selected blogs to determine a trend related to the selected media program and a graphical user interface is presented that concurrently presents the selected blogs, the trend, and the selected media program. Other embodiments are disclosed.

Abstract: Systems and methods are provided to collect, analyze and report social media aggregated from a plurality of social media websites. Social media is retrieved from social media websites, analyzed for sentiment, and categorized by topic and user demographics. The data is then archived in a data warehouse and various interfaces are provided to query and generate reports on the archived data. In some embodiments, the system further recognizes alert conditions and sends alerts to interested users. In some embodiments, the system further recognizes situations where users can be influenced to view a company or its products in a more favorable light, and automatically posts responsive social media to one or more social media websites.

Abstract: A system that incorporates teachings of the present disclosure may operate, for example, according to a method for identifying subsets of blogs from a collection of blogs according to a relevance of each subset of blogs to one of a plurality of media programs deliverable to a plurality of subscriber devices, determining for each subset of blogs one or more trends, detecting a subscriber device from the plurality of subscriber devices, selecting a media program from the plurality of media programs, selecting one of the subsets of blogs that is relevant to the media program, and supplying the subscriber device the selected subset of blogs with the one or more trends determined for the select subset of blogs. Other embodiments are disclosed.

Abstract: Systems and methods are provided to collect, analyze and report social media aggregated from a plurality of social media websites. Social media is retrieved from social media websites, analyzed for sentiment, and categorized by topic and user demographics. The data is then archived in a data warehouse and various interfaces are provided to query and generate reports on the archived data. In some embodiments, the system further recognizes alert conditions and sends alerts to interested users. In some embodiments, the system further recognizes situations where users can be influenced to view a company or its products in a more favorable light, and automatically posts responsive social media to one or more social media websites.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for collecting web data in order to create diverse language models. A system configured to practice the method first crawls, such as via a crawler operating on a computing device, a set of documents in a network of interconnected devices according to a visitation policy, wherein the visitation policy is configured to focus on novelty regions for a current language model built from previous crawling cycles by crawling documents whose vocabulary considered likely to fill gaps in the current language model. A language model from a previous cycle can be used to guide the creation of a language model in the following cycle. The novelty regions can include documents with high perplexity values over the current language model.

Abstract: A system that incorporates teachings of the present disclosure may operate, for example, according to a method for identifying subsets of blogs from a collection of blogs according to a relevance of each subset of blogs to one of a plurality of media programs deliverable to a plurality of subscriber devices, determining for each subset of blogs one or more trends, detecting a subscriber device from the plurality of subscriber devices, selecting a media program from the plurality of media programs, selecting one of the subsets of blogs that is relevant to the media program, and supplying the subscriber device the selected subset of blogs with the one or more trends determined for the select subset of blogs. Other embodiments are disclosed.