Machine-learning tool for generating segmentation and topic metadata for documents

A system comprising:

• a memory device including a trained segmentation-and-labeling model configured by an accompanying training parameter set to predict segment bounds and classify resulting predicted segments into topics;
• and
• a processing device coupled to the memory device to perform operations comprising:
• accessing an input document;
• generating a predicted segment for the input document by applying a segmentation network of the trained segmentation-and-labeling model to an encoded text portion from the input document;
• generating a topic for the predicted segment by applying a pooling network of the trained segmentation-and-labeling model to the predicted segment;
• assembling, using the predicted segment and the topic, an output document including the input document, segment metadata identifying the predicted segment, and topic metadata identifying the topic;
• and
• storing or displaying the output document.

A non-transitory computer-readable medium storing executable instructions, which when executed by a processing device, cause the processing device to perform operations comprising:

• accessing an input document;
• accessing a trained segmentation-and-labeling model configured by an accompanying training parameter set to predict segment bounds and classify resulting predicted segments into one or more topics;
• a step for jointly segmenting and labeling the input document by using a segmentation network and a pooling network, both from the trained segmentation-and-labeling model, to produce segment metadata identifying segments, and topic metadata identifying topics of the segments;
• assembling an output document having the input document, the segment metadata and the topic metadata;
• and
• storing or displaying the output document.