Oracle International Corporation

Tao Sheng

Jun Qian

Mengqing Guo

Yazhe Hu

Jeaff Wang

Wenjing Yang

Mohammadhossein Chaghazardi

Techniques are described for HTML-based image generation. An example, method can include generating hypertext markup language (HTML) code for a table comprising a table structure of a set of rows and columns. The method can further include generating HTML code for a text to populate a cell of the table. The method can further include generating a rendered image of the table using the HTML code. The method can further include detecting a first pixel of the rendered image comprising the first color, and a second pixel of the rendered image comprising the second color. The method can further include detecting the text on the rendered image. The method can further include generating a bounding box, surrounding the detected text. The method can further include generating annotation comprising a bounding box parameter and a text parameter.

Synthetic table generation pipeline for training deep table extraction models

Automated techniques are for generating a large volume of diverse training data that can be used for training machine learning models to extract KV pairs from document images. Given a single input document image and associated annotation data, a large number of diverse synthetic training datapoints are automatically generated by a synthetic data generation system, each datapoint including a synthetic document image and associated annotation data. The generated synthetic training datapoints can be used to train and improve the performance of ML models for extracting KV pairs from document images. In certain implementations, multiple synthetic datapoints are generated by varying the values associated with a key for a content item within the input document image.

Generating synthetic training data including document images with key-value pairs

Techniques for multi-stage training of a machine learning model to extract key-value pairs from documents are disclosed. A system trains a machine learning model using a set of training data including unlabeled documents of various document categories. The initial stage identifies relationships among tokens, or words, numbers, and punctuation, in documents. The system re-trains the machine learning model using a set of training data which includes a particular category of documents while excluding other categories of documents. The second training stage is a supervised machine learning stage in which the training data is labeled to identify key-value pairs in the documents. In the initial training stage, the system sets parameters of the machine learning model to an initial state. In the second stage, the system modifies the parameters of the machine learning model based on the characteristics of the training data set including the documents of the particular category.

Growing community of inventors

Bellevue, WA, United States of America

Tao Sheng