Had just mentioned this classic AI problem, was pointed to work underway by Microsoft, which points to this. Pointd to the article below, which after the abstract gets technical. Like I have mentioned before, its what humans do well, and is a subtask of common conversation. Absorbing what others say, summarizing it based on context and what we understood, asking for clarification and formulating some measure of our understanding.
STRUCTURED NEURAL SUMMARIZATION
Patrick Fernandes, Miltiadis Allamanis & Marc Brockschmidt
Microsoft Research
Cambridge, United Kingdom
Summarization of long sequences into a concise statement is a core problem in natural language processing, requiring non-trivial understanding of the input. Based on the promising results of graph neural networks on highly structured data, we develop a framework to extend existing sequence encoders with a graph component that can reason about long-distance relationships in weakly structured data such as text. In an extensive evaluation, we show that the resulting hybrid sequence-graph models outperform both pure sequence models as well as pure graph models on a
range of summarization tasks.
INTRODUCTION
Summarization, the task of condensing a large and complex input into a smaller representation that
retains the core semantics of the input, is a classical task for natural language processing systems. Automatic summarization requires a machine learning component to identify important entities and
relationships between them, while ignoring redundancies and common concepts ... "
Summarized in
a Venturebeat article.
See also Google's work in this at Summarization tag. See also work by
Salesforce in this area that slipped my mind,, will be reviewing that.