Abstract: This disclosure relates to methods, non-transitory computer readable media, and systems apply machine-learning techniques and computational analysis to extract topics from textual content and reconnect the textual content with the extracted topics. To illustrate, the disclosed systems utilize a topic generation model to generate a topic data structure (including extracted topics and associated keywords) from unstructured text based on underlying themes within the unstructured text. Furthermore, the disclosed systems utilize a reverb correlation model to reconnect the unstructured text to the extracted topics by determining correlations between the text and the extracted topics. Additionally, in certain embodiments, the disclosed systems utilize a reverb correlation model (and/or additional models) to provide detailed explanations of the reasons particular text is correlated with particular topics.

Abstract: Implementations analyze transaction data and objectively capture pre-identified desired information about the analyzed transaction data in a consistently organized manner. An example system includes a user interface that enables a user to provide static portions and dynamic portions of a template. The dynamic portions identify variables that are replaced with either data extracted from the transaction or text based on the output of classifiers applied to the transaction. An example method includes applying classifiers to scoring units of a transaction to generate classifier tags for the scoring units and generating a narrative by replacing variables in an automated narrative template with text based on at least some of the classifier tags.

Abstract: Implementations analyze transaction data and objectively capture pre-identified desired information about the analyzed transaction data in a consistently organized manner. An example system includes a user interface that enables a user to provide static portions and dynamic portions of a template. The dynamic portions identify variables that are replaced with either data extracted from the transaction or text based on the output of classifiers applied to the transaction. An example method includes applying classifiers to scoring units of a transaction to generate classifier tags for the scoring units and generating a narrative by replacing variables in an automated narrative template with text based on at least some of the classifier tags.

Abstract: Implementations analyze transaction data and objectively capture pre-identified desired information about the analyzed transaction data in a consistently organized manner. An example system includes a user interface that enables a user to provide static portions and dynamic portions of a template. The dynamic portions identify variables that are replaced with either data extracted from the transaction or text based on the output of classifiers applied to the transaction. An example method includes applying classifiers to scoring units of a transaction to generate classifier tags for the scoring units and generating a narrative by replacing variables in an automated narrative template with text based on at least some of the classifier tags.