I'm trying to create a question answering engine over linked data, which answers questions about famous people. The data set that I'm using is DBPedia.

Right now, I'm working on the NLP part where I'm converting the user given natural language question to the sparql query. I've read papers on NLPreduce, ginseng, freya, poweraqua and other few template based papers that gives various ways to parse the natural language question. Could you please point out the pros and cons of these systems and also show other methods if there are any. Thanks in advance

asked 18 Feb '13, 15:19

byteofprash's gravatar image

accept rate: 0%

Sorry, but if YOU read the papers, then it would be YOUR task to point out advantages and disadvantages of the systems. I'm also working on QA in Semenatic Web, and from what I learned so far, there is no "best way"(in my opinion).


answered 19 Feb '13, 03:15

AKSWMember's gravatar image

accept rate: 25%

Your answer
toggle preview

Follow this question

By Email:

Once you sign in you will be able to subscribe for any updates here



Answers and Comments

Markdown Basics

  • *italic* or _italic_
  • **bold** or __bold__
  • link:[text](http://url.com/ "Title")
  • image?![alt text](/path/img.jpg "Title")
  • numbered list: 1. Foo 2. Bar
  • to add a line break simply add two spaces to where you would like the new line to be.
  • basic HTML tags are also supported



Asked: 18 Feb '13, 15:19

Seen: 932 times

Last updated: 19 Feb '13, 03:24