Abstract: In some embodiments, techniques are provided for document identification using a multimodal model that has been trained using one-shot learning. In one example, a first method of document image processing includes generating, for each template document image of a plurality of template document images, a corresponding fingerprint of a plurality of fingerprints; and based on the plurality of fingerprints, training a multimodal model. For each template document image of the plurality of template document images, generating the corresponding fingerprint may include detecting a plurality of regions within the template document image, wherein the plurality of regions comprises a plurality of text regions; and filtering the plurality of regions to obtain a plurality of regions of interest, wherein the fingerprint is based on the plurality of regions of interest.

Abstract: A process for document processing (e.g., automated package splitting) may involve producing, for each document page of an ordered plurality of document pages, an image of the document page and a representation of text from the document page; generating, for each document page of the ordered plurality, and based on the image of the document page and the representation of text from the document page, an embedding of the document page; and generating, for each document page among a subset of the ordered plurality, a label for the document page that indicates whether the document page is a document first page, based on the embedding of the document page, the embedding of each of at least one document page that precedes the document page in the ordered plurality, and the embedding of each of at least one document page that follows the document page in the ordered plurality.

Abstract: A process for document processing (e.g., automated package splitting) may involve producing, for each document page of an ordered plurality of document pages, an image of the document page and a representation of text from the document page; generating, for each document page of the ordered plurality, and based on the image of the document page and the representation of text from the document page, an embedding of the document page; and generating, for each document page among a subset of the ordered plurality, a label for the document page that indicates whether the document page is a document first page, based on the embedding of the document page, the embedding of each of at least one document page that precedes the document page in the ordered plurality, and the embedding of each of at least one document page that follows the document page in the ordered plurality.

Abstract: In some embodiments, techniques for self-labeling to extract a representative set of samples from a large-scale set of unlabeled documents (e.g., a set that represents a distribution of the large-scale set) are provided. The samples of the representative set may then be used to classify the documents of the large-scale set.

Abstract: In some embodiments, techniques for knowledge-based validation of entities extracted from digital documents are provided. For example, a process may involve selecting, from among a plurality of entities extracted from a digital document, a first set of correlated entities. Selecting the first set of correlated entities may be based on a correlation that is indicated by relative location of the entities of the first set of correlated entities within the digital document or by similarity among tags of the entities of the first set. The method may also include determining, using a knowledge model, that the first set of correlated entities is not valid; and generating, using the knowledge model, a first modified set of correlated entities, wherein each entity of the first modified set of correlated entities corresponds to a respective entity of the first set of correlated entities.