Systems and methods for parsing natural language sentences using an artificial neural network (ANN) are described. Embodiments of the described systems and methods may generate a plurality of word representation matrices for an input sentence, wherein each of the word representation matrices is based on an input matrix of word vectors, a query vector, a matrix of key vectors, and a matrix of value vectors, and wherein a number of the word representation matrices is based on a number of syntactic categories, compress each of the plurality of word representation matrices to produce a plurality of compressed word representation matrices, concatenate the plurality of compressed word representation matrices to produce an output matrix of word vectors, and identify at least one word from the input sentence corresponding to a syntactic category based on the output matrix of word vectors.

Embodiments of the present disclosure include a method for token-position handling comprising: processing a first sequence of tokens to produce a second sequence of tokens, wherein the second sequence of tokens has a smaller number of tokens than the first sequence of tokens; masking at least some tokens in the second sequence to produce masked tokens; moving the masked tokens to the beginning of the second sequence to produce a third sequence; encoding tokens in the third sequence into a set of numeric vectors in a first array; and processing the first array in a transformer neural network to determine correlations among the third sequence, the processing the first array producing a second array.

The present disclosure relates generally to systems and processes for position fulfillment and, more particularly, to systems and methods of identifying and matching human resources to an open employment position within an organization. The method includes: obtaining, by a computer system, one or more profiles from one or more data sources; analyzing, by the computer system, the one or more profiles to parse attributes and find similarities and/or recurring occurrences in the parsed attributes; normalizing the parsed attributes based on the at least one similarities and recurring occurrences; and matching the normalized attributes to attributes of an open position.

Sentiment classification can be implemented by an entity-level multimodal sentiment classification neural network. The neural network can include left, right, and target entity subnetworks. The neural network can further include an image network that generates representation data that is combined and weighted with data output by the left, right, and target entity subnetworks to output a sentiment classification for an entity included in a network post.

Sentiment classification can be implemented by an entity-level multimodal sentiment classification neural network. The neural network can include left, right, and target entity subnetworks. The neural network can further include an image network that generates representation data that is combined and weighted with data output by the left, right, and target entity subnetworks to output a sentiment classification for an entity included in a network post.

Structured documents are processed using convolutional neural networks. For example, the processing can include receiving a rendered form of a structured document; mapping a grid of cells to the rendered form; assigning a respective numeric embedding to each cell in the grid, comprising, for each cell: identifying content in the structured document that corresponds to a portion of the rendered form that is mapped to the cell, mapping the identified content to a numeric embedding for the identified content, and assigning the numeric embedding for the identified content to the cell; generating a matrix representation of the structured document from the numeric embeddings assigned to the cells of the grids; and generating neural network features of the structured document by processing the matrix representation of the structured document through a subnetwork comprising one or more convolutional neural network layers.

Certain aspects of the disclosure are directed to monitoring user-data communications corresponding to a user-generated message. According to a specific example, user-data communications, which are addressed to a client among a plurality of remotely-situated client entities, are directed to a message recording system. Each of the plurality of remotely-situated client entities are respectively configured and arranged to interface with a data communications server providing data communications services on a subscription basis. During recording of a message associated with the user-data communications and on the message recording system, speech characteristic parameters of the message may be analyzed, and a sentiment score and a criticality score for the message, may be determined. During the recording of the message, the user-data communications may be routed based on the determined sentiment score and criticality score.

A method to automatically classify emails may include generating multiple entity data objects using entities identified in receiver and sender fields of emails and categorizing the multiple entity data objects into a first set of data objects and a second set of data objects. The method may also include extracting all tokens from each email and searching the extracted tokens for tokens associated with the data objects of the first set of data objects. The method may further include identifying the emails that include the extracted tokens that are associated with the data objects of the first set of data objects, identifying a particular data object of the first set of data objects to which an identified email corresponds, and automatically classifying the identified email in the first category in response to identifying the particular data object of the first set of data objects to which an identified email corresponds.

A method to automatically classify emails may include generating multiple entity data objects using entities identified in receiver and sender fields of emails and categorizing the multiple entity data objects into a first set of data objects and a second set of data objects. The method may also include extracting all tokens from each email and searching the extracted tokens for tokens associated with the data objects of the first set of data objects. The method may further include identifying the emails that include the extracted tokens that are associated with the data objects of the first set of data objects, identifying a particular data object of the first set of data objects to which an identified email corresponds, and automatically classifying the identified email in the first category in response to identifying the particular data object of the first set of data objects to which an identified email corresponds.

A system and method for translating questions into database queries are provided. A text to database query system receives a natural language question and a structure in a database. Question tokens are generated from the question and query tokens are generated from the structure in the database. The question tokens and query tokens are concatenated into a sentence and a sentence token is added to the sentence. A BERT network generates question hidden states for the question tokens, query hidden states for the query tokens, and a classifier hidden state for the sentence token. A translatability predictor network determines if the question is translatable or untranslatable. A decoder converts a translatable question into an executable query. A confusion span predictor network identifies a confusion span in the untranslatable question that causes the question to be untranslatable. An auto-correction module to auto-correct the tokens in the confusion span.