Abstract: A method of categorizing text entries on a document can include determining, for each of a plurality of text bounding boxes in the document, respective text, respective coordinates, and respective input embeddings. The method may further include defining a graph of the plurality of bounding boxes, the graph comprising a plurality of connections among the plurality of bounding boxes, each connection comprising a first and second bounding box and zero or more respective intermediate bounding boxes. The method may further include determining a respective attention value for each connection according to a quantity of intermediate bounding boxes in the connection and, based on a the respective attention values and a transformer-based machine learning model applied to the respective input embeddings and respective coordinates, determining output embeddings for each bounding box and, based on the respective output embeddings, generating a bounding box label for each bounding box.

Abstract: Systems/techniques for facilitating context-enhanced category classification are provided. In various embodiments, a system can access a first textual description of a product or service. In various aspects, the system can identify, via execution of named entity recognition, one or more keywords in the first textual description. In various instances, the system can access, from a set of queryable databases, one or more second textual descriptions that respectively correspond to the one or more keywords. In various cases, the system can generate, via execution of word embedding, a first numerical representation of the first textual description and one or more second numerical representations of the one or more second textual descriptions. In various aspects, the system can identify, via execution of a machine learning classifier, a category label for the product or service, based on the first numerical representation and the one or more second numerical representations.

Abstract: Methods and systems are presented for generating and using a machine learning model configured to perform cross-domain named entity recognition. The machine learning model is generated to accept a sentence associated with a target domain and to predict, for at least a word in the sentence, a corresponding entity associated with the target domain, without having been trained using training data associated with the target domain. In particular, the machine learning model is trained using only training data associated with a source domain. Based on derived relationships between entities associated with the source domain and entities associated with the target domain, the machine learning model is configured to transfer knowledge associated with the source domain to the target domain such that the machine learning model can map words within a sentence to entities associated with the target domain.