Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for providing a timeline in response to search terms. In one aspect, a method includes receiving a query that includes search terms and time constraints and determining multiple time intervals from the time period, and for each time interval, receiving data identifying resources that are responsive to the search terms and that each have a publication date that specifies a date that is within the time interval, and determining, from the identified resources for the time interval, a number of the resources that are hosted by a host that belongs to a predefined category. The method includes selecting time intervals for which the respective number of identified resources for the respective time interval meets a selection threshold and providing a graphical depiction of the selected time intervals as a response to the query.

Abstract: Embodiments herein provide computer-implemented techniques for allowing a user computing device to extract financial card information using optical character recognition (“OCR”). Extracting financial card information may be improved by applying various classifiers and other transformations to the image data. For example, applying a linear classifier to the image to determine digit locations before applying the OCR algorithm allows the user computing device to use less processing capacity to extract accurate card data. The OCR application may train a classifier to use the wear patterns of a card to improve OCR algorithm performance. The OCR application may apply a linear classifier and then a nonlinear classifier to improve the performance and the accuracy of the OCR algorithm. The OCR application uses the known digit patterns used by typical credit and debit cards to improve the accuracy of the OCR algorithm.

Abstract: Embodiments herein provide computer-implemented techniques for allowing a user computing device to extract financial card information using optical character recognition (“OCR”). Extracting financial card information may be improved by applying various classifiers and other transformations to the image data. For example, applying a linear classifier to the image to determine digit locations before applying the OCR algorithm allows the user computing device to use less processing capacity to extract accurate card data. The OCR application may train a classifier to use the wear patterns of a card to improve OCR algorithm performance. The OCR application may apply a linear classifier and then a nonlinear classifier to improve the performance and the accuracy of the OCR algorithm. The OCR application uses the known digit patterns used by typical credit and debit cards to improve the accuracy of the OCR algorithm.

Abstract: Methods and apparatus for determining the effectiveness of web pages are described. For each of a plurality of conversion points corresponding to a particular product or service, a plurality of paths leading to the conversion point are determined. Each of the plurality of paths leading to the conversion point includes a plurality of web pages connected by links. Each web page is characterized with respect to each of selected ones of the plurality of conversion points which may be reached from the web page via at least one of the paths. Characterizing each web page and/or its content includes determining a measure of effectiveness which represents a likelihood that viewing of the web page will lead to one or more of the selected conversion points.

Abstract: A system for translating a first word set in a source language into a second word set in a target language, the system comprising: input means for inputting the first word set into the system; tagging means for tagging the first word set input to the system so as to at least substantially reduce non-essential variability in the first word set; translation means including a single a posteriori conditional probability model and a target candidate store for storing target language candidate word sets, wherein the translation means employs the single model to evaluate the target language candidate word sets in order to select the target language candidate word set having a best score with respect to the first word set; and output means for outputting the best scoring target language candidate word set as the second word set in the target language.