Natural language processing for numerical data recognition

Question

My requirement is to recognize and extract numerical data from a natural language sentence (English only) in response to queries. Java platform. For example, if the user request is "What is the height of the Mount Everest", and we have a paragraph like:

In 1856, the Great Trigonometric Survey of British India established the first published height of Everest, then known as Peak XV, at an altitude of 29,002 feet (8,840 m). In 1865, Everest received its official English name from the Royal Geographical Society on the recommendation of Andrew Waugh, the British Inspector General of India at the time, who named him after his predecessor in office and former head of Sir George Everest. [4] The Homolungma was widely used by Tibetans for centuries, but Vog could not offer a local name because Nepal and Tibet were closed to foreigners. (Wikipedia insert)

To request the user "Mount Everest Height" from the paragraph, I need to get 29002 feet or 8840 m as an answer. Can anyone suggest any possible ways to do this in Java? Are there open source libraries for the same thing?

Answer 1

Obviously, doing this well is very difficult. If this is the destination, then I assume the expectation is a little lower. Here are some thoughts on getting you started:

; . 2 , , , . - , - . "" (, "", "", "", "" ). , , , - , , - ( "at", "the", "of", .).

, . , . . , ( ). , "" , . "", , "". , "" "km, ft, in, cm, m" .. , .

, . , . .