A new AI algorithm summarizes text amazingly well


An algorithm developed by researchers at Salesforce shows how computers may eventually take on the job of summarizing documents. The system learns from examples of good summaries, an approach called supervised learning, but also employs a kind of artificial attention to the text it is ingesting and outputting. Kristian Hammond, a professor at Northwestern University, and the founder of Narrative Science, a company that generates narrative reports from raw data, says the Salesforce research is a good advance, but it also shows the limits of relying purely on statistical machine learning. A startup called Maluuba, which was acquired earlier this year by Microsoft, recently produced a system capable of generating relevant questions from text.