Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for implementing long-short term memory cells with saturating gating functions. One of the systems includes a first Long Short-Term Memory (LSTM) cell, wherein the first LSTM cell is configured to, for each of the plurality of time steps, generate a new cell state and a new cell output by applying a plurality of gates to a current cell input, a current cell state, and a current cell output, each of the plurality of gates being configured to, for each of the plurality of time steps: receive a gate input vector, generate a respective intermediate gate output vector from the gate input, and apply a respective gating function to each component of the respective intermediate gate output vector, wherein the respective gating function for at least one of the plurality of gates is a saturating gating function.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for implementing long-short term memory cells with saturating gating functions. One of the systems includes a first Long Short-Term Memory (LSTM) cell, wherein the first LSTM cell is configured to, for each of the plurality of time steps, generate a new cell state and a new cell output by applying a plurality of gates to a current cell input, a current cell state, and a current cell output, each of the plurality of gates being configured to, for each of the plurality of time steps: receive a gate input vector, generate a respective intermediate gate output vector from the gate input, and apply a respective gating function to each component of the respective intermediate gate output vector, wherein the respective gating function for at least one of the plurality of gates is a saturating gating function.

Abstract: A system and method of processing an image of a document using an optical character recognition process is disclosed. In one example, the method comprises acts of extracting, by a computer system, a plurality of recognizable units from the document, extracting, by the computer system, a plurality of features from the plurality of recognizable units, separating, by the computer system, the plurality of recognizable units, based on the plurality of extracted features into a plurality of fragments having at least one fragment type, determining a distance metric between the plurality of recognizable units, based on the plurality of extracted features, and classifying, by the computer system, the plurality of recognizable units into a plurality of clusters based on the distance metric, each cluster including a set of recognizable units associated with a shape classification.

Abstract: A system and method of assigning diacritics in an electronic image using optical character recognition (OCR) is disclosed. In one example, the method comprises analyzing, by a computer system, the electronic image to generate a plurality of bounding blocks associated with text lines within the electronic image. The method further comprises establishing a plurality of bounding boxes for diacritics and base text with the electronic image. The method also comprises determining a distance from a diacritic to a nearest base text character and a nearest text line. The method also comprises evaluating a base box distance and the nearest text line distance to assign the diacritic to a correct text line in the electronic image.

Abstract: A system and method of extracting formulas in an electronic image of a document using optical character recognition (OCR) is disclosed. In one example, the method comprises analyzing the electronic image, including a plurality of text lines, to generate a plurality of bounding blocks, each bounding block associated with a text line detected within the electronic image, searching the plurality of text lines to detect at least one character matching one of a plurality of character groups, calculating a symbol density of each of the plurality of character groups for each of the plurality of text lines, and classifying each of the plurality of text lines as at least one of an equation block type, an inline equation block type, and a descriptive block type, based on the symbol density, wherein each of the plurality of text lines classified as the equation block type is extracted.