uima-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Petr Baudis <pa...@ucw.cz>
Subject Re: Fwd: Lexical answer detection, focus word detection support in UIMA
Date Thu, 18 Dec 2014 11:28:23 GMT
  Hi!

On Thu, Dec 18, 2014 at 04:31:35PM +0530, Karimkhan Pathan wrote:
> Lexical answer type detection, focus word detection, these functionalities
> are available in IBM UIMA. This is mentioned by one of UIMA contributor at
> http://www3.cs.stonybrook.edu/~pfodor/courses/CSE392/L0-CourseInformation.pdf
> and also in http://arxiv.org/pdf/0809.0680.pdf
> 
> I want to know whether this functionalities are available in  Apache UIMA
> Version 2.6.0 (UIMA Java framework & SDK
> <http://uima.apache.org/d/uimaj-2.6.0/RELEASE_NOTES.html>) . I go through
> it, but could see only basic name, email annotators only.

  UIMA is just the generic framework for annotating and processing
unstructured data, plus a few simple examples.  Components of the DeepQA
(IBM Watson) Jeopardy player are not open source or part of core UIMA.

  However, you can go a long way with even a few very simple rules based
on the dependency parse of the question:

	https://github.com/brmson/yodaqa/blob/master/src/main/java/cz/brmlab/yodaqa/analysis/question/FocusGenerator.java

-- 
				Petr Baudis
	If you do not work on an important problem, it's unlikely
	you'll do important work.  -- R. Hamming
	http://www.cs.virginia.edu/~robins/YouAndYourResearch.html

Mime
View raw message