[Attempto] Broader the range of texts that can be mapped to ACE

[Norbert E. Fuchs]

On 17 Jan 2013, at 16:25 , Jean-Marc Vanel <jeanmarc.vanel at gmail.com> wrote:

> I thought of a way to broader the range of texts that can be mapped to ACE.
> Would that make sense to train a text machine learning algorithm with
> texts in natural english and their translation in ACE?
> I guess some of you already translated manually some domain and
> software specifications into ACE. That could become a training set.

Jean-Marc

In the paper

D. Mollá, R. Schwitter. From Plain English to Controlled English. In: Proceedings of the 2001 Australasian Natural Language Processing Workshop, 20th April 2001, Macquarie University, Sydney, Australia, pp. 77-83, April 2001.

http://web.science.mq.edu.au/~rolfs/papers/anlp2001.pdf

Mollá and Schwitter describe the limits of automatically going from plain English to controlled English.

In my view, natural English and controlled English are conceptually different languages that need a human translator. 

For a comparison take a text problem: A farmer has a number of cows and a number of ducks. Altogether the farmer has 100 animals that have 260 feet. How many cows and ducks does the farmer have?

To solve the problem you need to translate the English version of the problem into the language of mathematics.

Notice first that you need to add knowledge, for instance that cows and ducks are animals, that no cow is a duck, and that cows have 4 feet and ducks 2 feet.

Notice second that in order to arrive at the mathematical expression of the problem – namely the linear equations X+Y=100, 4*X+2*Y=260, where X is the number of cows and Y the number of ducks – you need to do some abstraction and need to find a strategy how to solve the problem.

Translating natural English into ACE requires similar abstraction processes that might partially be automated by using machine translation, but as the paper of Mollá and Schwitter human intervention will still be needed. Only think of information that is missing in the natural English but needed in the ACE text.

Best regards.

   --- nef