Methods, apparatus, systems and articles of manufacture are disclosed for receipt decoding. An example apparatus includes processor circuitry to execute instructions to extract text from the receipt image, the text including bounding boxes; associate ones of the bounding boxes to link horizontally related fields of a the receipt image by selecting a first bounding box; identifying first horizontally aligned bounding boxes, the first horizontally aligned bounding boxes to include at least one bounding box of the bounding boxes that is horizontally aligned relative to the first bounding box; adding the first horizontally aligned bounding boxes to a word sync list; and connecting ones of the first horizontally aligned bounding boxes and the first bounding box based on at least one of an amount of the first horizontally aligned bounding boxes in the word sync list and a relationship among the first horizontally aligned bounding boxes and the first bounding box.

An aspect of the disclosed technology comprises a test-time adaptation (“TTA”) technique for visual document understanding (“VDU”) tasks that uses self-supervised learning on different modalities (e.g., text and layout) by applying masked visual language modeling (“MVLM”) along with pseudo-labeling. In accordance with an aspect of the disclosed technology, the TTA technique enables a document model to adapt to domain or distribution shifts that are detected.

Provided are a classification method and apparatus, an electronic device and a storage medium, which relate to the field of artificial intelligence and in particular, to the fields of natural language processing and deep learning. The classification method comprises: performing coding processing on to-be-classified data to obtain a to-be-classified coding feature; determining reference coding features of reference classification data similar to the to-be-classified data according to the to-be-classified coding feature; and determining a target category of the to-be-classified data according to the reference coding features and reference categories of the reference classification data.

Implementations include receiving sample data, the sample data being generated as digital data representative of a sample of the product, providing a set of features by processing the sample data through multiple layers of a residual network, a first layer of the residual network identifying one or more features of the sample data, and a second layer of the residual network receiving the one or more features of the first layer, and identifying one or more additional features, processing the set of features using a CNN to identify a set of regions, and at least one object in a region of the set of regions, and determine a type of the at least one object, and selectively issuing an alert at least partially based on the type of the at least one object, the alert indicating contamination within the sample of the product.

Methods, apparatus, systems and articles of manufacture are disclosed for receipt decoding. An example apparatus for processing a receipt associated with a user disclosed herein includes an optical character recognition engine to generate bounding boxes, respective ones of the bounding boxes associated with groups of characters detected in the receipt, the bounding boxes including a first bounding box, a second bounding box and a third bounding box, a word connector to connect the first bounding box to the second bounding box based on (1) an adjacency of the first bounding box to the second bounding box and (2) a difference value from a comparison of a location of the first bounding box to a location of the second bounding box, a line connector to form a line of the ones of the bounding boxes by connecting the third bounding box to the second bounding based on a relationship between the first bounding box and the second bounding box, the line of the ones of the bounding boxes indicative of related receipt fields, and a creditor to generate a report based on the line.

Methods, apparatus, systems and articles of manufacture are disclosed for receipt decoding. An example apparatus for processing a receipt associated with a user disclosed herein includes an optical character recognition engine to generate bounding boxes, respective ones of the bounding boxes associated with groups of characters detected in the receipt, the bounding boxes including a first bounding box, a second bounding box and a third bounding box, a word connector to connect the first bounding box to the second bounding box based on (1) an adjacency of the first bounding box to the second bounding box and (2) a difference value from a comparison of a location of the first bounding box to a location of the second bounding box, a line connector to form a line of the ones of the bounding boxes by connecting the third bounding box to the second bounding based on a relationship between the first bounding box and the second bounding box, the line of the ones of the bounding boxes indicative of related receipt fields, and a creditor to generate a report based on the line.

Methods, systems, and computer-readable storage media for receiving input data including a set of entities of a first type and a set of entities of a second type, providing a set of features based on entities of the first type, the set of features including features expected to be included in entities of the second type, filtering entities of the second type based on the set of features to provide a sub-set of entities of the second type, and generating an output by processing the set of entities of the first type and the sub-set of entities of the second type through a ML model, the output comprising a set of matching pairs, each matching pair in the set of matching pairs comprising an entity of the set of entities of the first type and at least one entity of the sub-set of entities of the second type.

Implementations include receiving sample data, the sample data being generated as digital data representative of a sample of the product, providing a set of features by processing the sample data through multiple layers of a residual network, a first layer of the residual network identifying one or more features of the sample data, and a second layer of the residual network receiving the one or more features of the first layer, and identifying one or more additional features, processing the set of features using a CNN to identify a set of regions, and at least one object in a region of the set of regions, and determine a type of the at least one object, and selectively issuing an alert at least partially based on the type of the at least one object, the alert indicating contamination within the sample of the product.

Systems and methods for dynamically generating a predicted similarity score for a pair of input sequences. A predicted similarity score for a pair of input sequences is determined based at least in part on at least one of a token-level similarity probability score for the pair of input sequences, a target region match indication for the pair of input sequences, a fuzzy match score for the pair of input sequences, a character-level match score for the pair of input sequences, one or more similarity ratio occurrence indicators for the pair of input sequences, and a harmonic mean score of the fuzzy match score for the pair of input sequences and the token-level similarity probability score for the pair of input sequences.

A method and system for a feature subset-classifier pair for a classification task. The classification task corresponds to automatically classifying data associated with a subject(s) or object(s) of interest into an appropriate class based on a feature subset selected among a plurality of features extracted from the data and a classifier selected from a set of classifier types. The method proposed includes simultaneously determining the feature subset-classifier pair based on a relax-greedy {feature subset, classifier} approach utilizing sub-greedy search process based on a patience function, wherein the feature subset-classifier pair provides an optimal combination for more accurate classification. The automatic joint selection is time efficient solution, effectively speeding up the classification task.