Abstract: Methods, systems, and computer-readable storage media for receiving a first bank statement at a hybrid pipeline including a set of lookup tables and a deep learning (DL) model that can each be used to determine customer IDs from bank statements, providing a first key based on data associated with the first bank statement, and determining that the first key is included in a first lookup table of the set of lookup tables, and in response: identifying a first set of customer IDs from the first lookup table, the first set of customer IDs including one or more customer IDs, and outputting the first set of customer IDs to computer-executable software that matches the first bank statement to one or more electronic documents at least partially based on the first set of customer IDs.

Abstract: Methods, systems, and computer-readable storage media for providing, by a machine learning (ML) platform, a first binary classifier, processing, by the first binary classifier a super-set of invoices to provide a plurality of sets of invoices based on matching pairs of invoices in the super-set of invoices, providing, by the ML platform, a second binary classifier, processing, by the second binary classifier, a bank statement and the plurality of sets of invoices to define two or more super-invoices based on aggregate features of invoices in the plurality of sets of invoices, and match the bank statement to a super-invoice of the two or more super-invoices, and outputting a match of the bank statement to the super-invoice.

Abstract: Methods, systems, and computer-readable storage media for a machine learning (ML) model and framework for training of the ML model to enable the ML model to correctly match entities even in instances where new entities are added after the ML model has been trained. More particularly, implementations of the present disclosure are directed to a ML model provided as a neural network that is trained to provide a scalar confidence score that indicates whether two entities in a pair of entities are considered a match, even if an entity in the set of entities was not accounted for in training of the ML model.

Abstract: Methods, systems, and computer-readable storage media for receiving structured data including a set of columns and a set of rows, determining, for each column, a column width defining a number of characters, providing, for each row, a set of padded values, each padded value corresponding to a column and including a value and one or more padding characters, the value and the one or more padding values collectively having a length equal to a respective column width, defining a set of strings by, for each row, concatenating padded values in the set of padded values to provide a string, and training the ML model by providing, for each string in the set of strings, an embedding as an abstract representation of a record of a respective row and processing the embedding through an attention layer of the ML model.

Abstract: Methods, systems, and computer-readable storage media for tuning behavior of a machine learning (ML) model by providing an alternative loss function used during training of a ML model, the alternative loss function enhancing reliability of the ML model, calibrating the confidence of the ML model after training, and reducing risk in downstream tasks by providing a mapping between the confidence of the ML model to the expected accuracy of the ML model.

Abstract: Methods, systems, and computer-readable storage media for receiving a set of documents matched by a ML model, each document in the set of documents including a computer-readable electronic document, processing a set of pairwise features, the ML model, and the set of documents by an explanation framework to generate a set of raw explanations, the set of raw explanations including one or more raw explanations, each raw explanation including a pairwise feature and an importance score, for each raw explanation, identifying a natural language template based on the pairwise feature and the importance score, and populating the natural language template with one or more parameters provided from the set of documents to provide a natural language explanation for matching of the documents in the set of documents by the ML model.

Abstract: Methods, systems, and computer-readable storage media for contextual interpretation of a Japanese word are provided. A first set of characters representing Japanese words is received. The first set of characters are received is input to a neural network. The neural network is trained to processes characters based on bi-directional context interpretation. The first set of characters is processed by the neural network through a plurality of learning layers that process the first set of characters in an order of the first set of characters and in a reverse order to determine semantical meanings of the characters in the first set of characters. An alphabet representation of at least one character of the first set of characters representing a Japanese word is output. The alphabet representation corresponds to a semantical meaning of the at least one character within the first set of characters.

Abstract: Methods, systems, and computer-readable storage media for receiving structured data including a set of columns and a set of rows, determining, for each column, a column width defining a number of characters, providing, for each row, a set of padded values, each padded value corresponding to a column and including a value and one or more padding characters, the value and the one or more padding values collectively having a length equal to a respective column width, defining a set of strings by, for each row, concatenating padded values in the set of padded values to provide a string, and training the ML model by providing, for each string in the set of strings, an embedding as an abstract representation of a record of a respective row and processing the embedding through an attention layer of the ML model.

Abstract: Methods, systems, and computer-readable storage media for a machine learning (ML) model and framework for training of the ML model to enable the ML model to correctly match entities even in instances where new entities are added after the ML model has been trained. More particularly, implementations of the present disclosure are directed to a ML model provided as a neural network that is trained to provide a scalar confidence score that indicates whether two entities in a pair of entities are considered a match, even if an entity in the set of entities was not accounted for in training of the ML model.

Abstract: Methods, systems, and computer-readable storage media for tuning behavior of a machine learning (ML) model by providing an alternative loss function used during training of a ML model, the alternative loss function enhancing reliability of the ML model, calibrating the confidence of the ML model after training, and reducing risk in downstream tasks by providing a mapping between the confidence of the ML model to the expected accuracy of the ML model.

Abstract: Methods, systems, and computer-readable storage media for receiving a first bank statement at a hybrid pipeline including a set of lookup tables and a deep learning (DL) model that can each be used to determine customer IDs from bank statements, providing a first key based on data associated with the first bank statement, and determining that the first key is included in a first lookup table of the set of lookup tables, and in response: identifying a first set of customer IDs from the first lookup table, the first set of customer IDs including one or more customer IDs, and outputting the first set of customer IDs to computer-executable software that matches the first bank statement to one or more electronic documents at least partially based on the first set of customer IDs.

Abstract: Methods, systems, and computer-readable storage media for receiving a set of training images and a set of classification labels, generating a set of target codebooks based on the set of classification labels, the set of target codebooks being provided as a first set of vectors of random value and dimension, generating a set of output codebooks based on the set of training images, the set of output codebooks being provided as a second set of vectors of random value and dimension, training a ML model by minimizing a loss function provided as a mean-squared-error (MSE) loss function, the loss function being measured by the Euclidean distance between an output codebook of the set of output codebooks and a target codebook of the set of target codebooks.

Abstract: Methods, systems, and computer-readable storage media for receiving a set of documents matched by a ML model, each document in the set of documents including a computer-readable electronic document, processing a set of pairwise features, the ML model, and the set of documents by an explanation framework to generate a set of raw explanations, the set of raw explanations including one or more raw explanations, each raw explanation including a pairwise feature and an importance score, for each raw explanation, identifying a natural language template based on the pairwise feature and the importance score, and populating the natural language template with one or more parameters provided from the set of documents to provide a natural language explanation for matching of the documents in the set of documents by the ML model.

Abstract: Methods, systems, and computer-readable storage media for contextual interpretation of a Japanese word are provided. A first set of characters representing Japanese words is received. The first set of characters are received is input to a neural network. The neural network is trained to processes characters based on bi-directional context interpretation. The first set of characters is processed by the neural network through a plurality of learning layers that process the first set of characters in an order of the first set of characters and in a reverse order to determine semantical meanings of the characters in the first set of characters. An alphabet representation of at least one character of the first set of characters representing a Japanese word is output. The alphabet representation corresponds to a semantical meaning of the at least one character within the first set of characters.

Abstract: Methods, systems, and computer-readable storage media for receiving, by a machine learning (ML) platform, a set of invoices including two or more invoices, processing, by the ML platform, each invoice through a neural network to provide respective invoice embeddings, each invoice embedding including a multi-dimensional vector, comparing, by the ML platform, invoice embeddings to define two or more super-invoices, each super-invoice including a sub-set of the set of invoices, and matching a bank statement to a super-invoice of the two or more super-invoices.

Abstract: Methods, systems, and computer-readable storage media for providing, by a machine learning (ML) platform, a first binary classifier, processing, by the first binary classifier a super-set of invoices to provide a plurality of sets of invoices based on matching pairs of invoices in the super-set of invoices, providing, by the ML platform, a second binary classifier, processing, by the second binary classifier, a bank statement and the plurality of sets of invoices to define two or more super-invoices based on aggregate features of invoices in the plurality of sets of invoices, and match the bank statement to a super-invoice of the two or more super-invoices, and outputting a match of the bank statement to the super-invoice.

Abstract: Methods, systems, and computer-readable storage media for providing a set of column pairs, each column pair including a column of a bank statement table, and a column of a super invoice table, each column pair corresponding to a modality, the super invoice table including at least one row including data associated with multiple invoices, for each column pair, determining a feature descriptor based on an operator, a feature vector being provided based on feature descriptors of the set of column pairs, inputting the feature vector to a ML model that processes the feature vector to determine a probability of a match between the bank statement, and a super invoice represented by the super invoice table, and outputting a binary output representing one of a match and no match between the bank statement, and the super invoice based on the probability.

Abstract: Methods, systems, and computer-readable storage media for receiving a set of training images and a set of classification labels, generating a set of target codebooks based on the set of classification labels, the set of target codebooks being provided as a first set of vectors of random value and dimension, generating a set of output codebooks based on the set of training images, the set of output codebooks being provided as a second set of vectors of random value and dimension, training a ML model by minimizing a loss function provided as a mean-squared-error (MSE) loss function, the loss function being measured by the Euclidean distance between an output codebook of the set of output codebooks and a target codebook of the set of target codebooks.