Abstract: A method of document image processing comprises, based on at least a document page image, generating a plurality of semantic tokens that includes a plurality of word tokens and a plurality of special tokens. Each special token among the plurality of special tokens represents a non-textual semantic element of the document image, and generating the plurality of semantic tokens includes predicting, for each special token among the plurality of special tokens, a token type of the special token. The method also comprises generating, for each semantic token among the plurality of semantic tokens, a corresponding semantic token embedding among a plurality of semantic token embeddings; and applying a trained model to process an input that is based on the plurality of semantic token embeddings and a plurality of visual token embeddings based on at least the document page image to generate a semantic processing result.

Abstract: An Artificial Intelligence (AI)-based data processing system employs a trained AI model for extracting features of products from various product classes and building a product ontology from the features. The product ontology is used to respond to user queries with product recommendations and customizations. Training data for the generation of the AI model for feature extraction is initially accessed and verified to determine of the training data meets a data density requirement. If the training data does not meet the data density requirement, data from one of a historic source or external sources is added to the training data. One of the plurality of AI models is selected for training based on the degree of overlap and the inter-class distance between the datasets of the various product classes within the training data.

Abstract: In some embodiments, techniques for document entity extraction are provided. For example, a process may involve processing document images to detect a plurality of regions of interest that includes text objects and non-text objects; for each of the plurality of regions of interest, producing a corresponding text string; and processing the text strings to identify entities. Processing the document images may involve applying a text object detection model to the document images to detect the text objects; and applying at least one non-text object detection model to the document images to detect the non-text objects. Prior to processing the document images, at least two object detection models among the text object detection model and the at least one non-text object detection model were generated by fine-tuning respective instances of a pre-trained object detection model.

Abstract: An Artificial Intelligence (AI)-based data processing system employs a trained AI model for extracting features of products from various product classes and building a product ontology from the features. The product ontology is used to respond to user queries with product recommendations and customizations. Training data for the generation of the AI model for feature extraction is initially accessed and verified to determine of the training data meets a data density requirement. If the training data does not meet the data density requirement, data from one of a historic source or external sources is added to the training data. One of the plurality of AI models is selected for training based on the degree of overlap and the inter-class distance between the datasets of the various product classes within the training data.