Abstract: A method includes executing a Optical Character Recognition (OCR) preprocessor on training images to obtain OCR preprocessor output, executing an OCR engine on the OCR preprocessor output to obtain OCR engine output, and executing an approximator on the OCR preprocessor output to obtain approximator output. The method further includes iteratively adjusting the approximator to simulate the OCR engine using the OCR engine output and the approximator output, and generating OCR preprocessor losses using the approximator output and target labels. The method further includes iteratively adjusting the OCR preprocessor using the OCR preprocessor losses to obtain a customized OCR preprocessor.

Abstract: Systems and methods for personalizing messages in a conversational chatbot are disclosed. An example method may include receiving clickstream event data corresponding to click events by users of an application, generating featurized clickstream data based at least in part on the received clickstream event data, determining one or more predicted intentions for a first user based at least in part on the featurized clickstream data, and generating one or more personalized messages for the first user based at least in part on the one or more predicted user intentions.

Abstract: A processor may generate a plurality of intermediate feature layers of an image using convolutional neural network (CNN) processing. For each intermediate feature layer, the processor may generate a plurality of text proposals using a region proposal network (RPN). Each text proposal may comprise a portion of the intermediate feature layer that is predicted to contain text. The processor may perform OCR processing on image data within a plurality of regions of the image to generate a text result for each region. Each region may comprise at least one of the text proposals. The processor may assemble the text results into a text string comprising the text results ordered according to a spatial order in which the plurality of regions appear within the image.

Abstract: A method may include extracting training tokens from a training corpus, generating training token features and training contextual features for each of the training tokens, training a probabilistic graphical model using classes, the training token features, and the training contextual features, extracting, from actual data, actual tokens including an actual token, generating actual token features and actual contextual features for each of the actual tokens, and classifying the actual token as a class using the probabilistic graphical model, the actual token features, and the actual contextual features.

Abstract: A processor may generate a plurality of intermediate feature layers of an image using convolutional neural network (CNN) processing. For each intermediate feature layer, the processor may generate a plurality of text proposals using a region proposal network (RPN). Each text proposal may comprise a portion of the intermediate feature layer that is predicted to contain text. The processor may perform OCR processing on image data within a plurality of regions of the image to generate a text result for each region. Each region may comprise at least one of the text proposals. The processor may assemble the text results into a text string comprising the text results ordered according to a spatial order in which the plurality of regions appear within the image.

Abstract: A method includes executing a Optical Character Recognition (OCR) preprocessor on training images to obtain OCR preprocessor output, executing an OCR engine on the OCR preprocessor output to obtain OCR engine output, and executing an approximator on the OCR preprocessor output to obtain approximator output. The method further includes iteratively adjusting the approximator to simulate the OCR engine using the OCR engine output and the approximator output, and generating OCR preprocessor losses using the approximator output and target labels. The method further includes iteratively adjusting the OCR preprocessor using the OCR preprocessor losses to obtain a customized OCR preprocessor.

Abstract: A processor may generate a plurality of intermediate feature layers of an image using convolutional neural network (CNN) processing. For each intermediate feature layer, the processor may generate a plurality of text proposals using a region proposal network (RPN). Each text proposal may comprise a portion of the intermediate feature layer that is predicted to contain text. The processor may perform OCR processing on image data within a plurality of regions of the image to generate a text result for each region. Each region may comprise at least one of the text proposals. The processor may assemble the text results into a text string comprising the text results ordered according to a spatial order in which the plurality of regions appear within the image.

Abstract: Systems and methods for personalizing messages in a conversational chatbot are disclosed. An example method may include receiving clickstream event data corresponding to click events by users of an application, generating featurized clickstream data based at least in part on the received clickstream event data, determining one or more predicted intentions for a first user based at least in part on the featurized clickstream data, and generating one or more personalized messages for the first user based at least in part on the one or more predicted user intentions.

Abstract: Arbitrary image data may be transformed into data suitable for optical character recognition (OCR) processing. A processor may generate a plurality of intermediate feature layers of an image using convolutional neural network (CNN) processing. For each intermediate feature layer, the processor may generate at least one text proposal using a region proposal network (RPN). The at least one text proposal may comprise a portion of the intermediate feature layer that is predicted to contain text. The processor may merge the text proposals with one another to form a patch of the image that is predicted to contain text. The processor may determine outer coordinates of the patch. The outer coordinates may comprise at least leftmost, rightmost, topmost, and bottommost coordinates. The processor may generate a quadrilateral of the image that is a smallest quadrilateral including the leftmost, rightmost, topmost, and bottommost coordinates.

Abstract: Systems and methods configured to provide automated and unsupervised inline question-answering in an online community.

Abstract: A system and method for information extraction character level features. The system and method may be used for data extraction for various types of content including a receipt or a tax form.

Abstract: Arbitrary image data may be transformed into data suitable for optical character recognition (OCR) processing. A processor may generate a plurality of intermediate feature layers of an image using convolutional neural network (CNN) processing. For each intermediate feature layer, the processor may generate at least one text proposal using a region proposal network (RPN). The at least one text proposal may comprise a portion of the intermediate feature layer that is predicted to contain text. The processor may merge the text proposals with one another to form a patch of the image that is predicted to contain text. The processor may determine outer coordinates of the patch. The outer coordinates may comprise at least leftmost, rightmost, topmost, and bottommost coordinates. The processor may generate a quadrilateral of the image that is a smallest quadrilateral including the leftmost, rightmost, topmost, and bottommost coordinates.

Abstract: A processor may generate a plurality of intermediate feature layers of an image using convolutional neural network (CNN) processing. For each intermediate feature layer, the processor may generate a plurality of text proposals using a region proposal network (RPN). Each text proposal may comprise a portion of the intermediate feature layer that is predicted to contain text. The processor may perform OCR processing on image data within a plurality of regions of the image to generate a text result for each region. Each region may comprise at least one of the text proposals. The processor may assemble the text results into a text string comprising the text results ordered according to a spatial order in which the plurality of regions appear within the image.

Abstract: The invention relates to a method for background removal from documents. The method includes obtaining an image of a document, performing a clustering operation on the image to obtain a plurality of image segments, and performing, for each image segment, a foreground/background classification to determine whether the image segment includes foreground. The method further includes obtaining an augmented image by combining the image segments that include foreground, and obtaining a background-treated image by cropping the image of the document, based on the foreground in the augmented image.

Abstract: A system and method for information extraction character level features. The system and method may be used for data extraction for various types of content including a receipt or a tax form.

Abstract: A method and system for generating synthetic form image involves obtaining a multitude of field value data and associated field labels for a chosen type of form document from an electronic data source, classifying the multitude of field value data into a multitude of data categories, where the multitude of data categories, learning statistical data distributions for categorical and numerical data types using the classified categorical and numerical data, and sampling data elements randomly using the learned data distributions to generate synthetic data for categorical and numerical data. The method also involves assembling the synthetic data for the multitude of data categories with the associated field labels to generate a labeled synthetic textual data set, rendering the labeled synthetic textual data set over a structured form layout image to produce a synthetic form image, and storing the synthetic form image and the labeled synthetic textual data set.

Abstract: A method may include extracting training tokens from a training corpus, generating training token features and training contextual features for each of the training tokens, training a probabilistic graphical model using classes, the training token features, and the training contextual features, extracting, from actual data, actual tokens including an actual token, generating actual token features and actual contextual features for each of the actual tokens, and classifying the actual token as a class using the probabilistic graphical model, the actual token features, and the actual contextual features.

Abstract: The invention relates to a method for background removal from documents. The method includes obtaining an image of a document, performing a clustering operation on the image to obtain a plurality of image segments, and performing, for each image segment, a foreground/background classification to determine whether the image segment includes foreground. The method further includes obtaining an augmented image by combining the image segments that include foreground, and obtaining a background-treated image by cropping the image of the document, based on the foreground in the augmented image.