Neural models for text generation are often designed in an end-to-end fashion, typically with zero control over intermediate computations, limiting their practical usability in downstream applications.
This task differs from other natural language generation tasks in the following ways: (1) The input is a set of identifiable entities (ICD codes) where the relations between individual entity are not explicitly specified.
Text segmentation plays an important role in various Natural Language Processing (NLP) tasks like summarization, context understanding, document indexing and document noise removal.
The method entrusts the summarizer to generate its own topically coherent sequential structures from scratch for effective communication.
Ideally a metric evaluating an abstract system summary should represent the extent to which the system-generated summary approximates the semantic inference conceived by the reader using a human-written reference summary.