Log in Help
Print
Homereleasesgate-2.0alpha3-build516doc 〉 ie.html
 

GATE

GATE and Information Extraction (IE)

GATE was originally developed in the context of IE R&D, and IE systems in many languages and shapes and sizes have been created using GATE and the IE components that have been distributed with it (see Maynard et al. 2000 for descriptions of some of these projects).

The principal architects of the IE systems in GATE version 1 were Robert Gaizauskas and Kevin Humphreys. This work lives on in the LaSIE system, and in many design ideas since taken up in the ANNIE system (see below) and other IE systems in Sheffield and elsewhere. A derivative of LaSIE was distributed with GATE version 1 under the name VIE, a Vanilla IE system.

GATE version 2 is distributed with an IE system called ANNIE, A Nearly-New IE system. ANNIE borrows a number of ideas from LaSIE (and a part-of-speech tagger from Mark Hepple), and contains a number of new ones, including a reliance on finite state algorithms and the JAPE language developed by Hamish Cunningham and Valentin Tablan.

ANNIE is currently a shallow processing system, and not suitable for event recognition. A full IE pipeline based on a LaSIE backend with ANNIE shallow analysis looks like this:

NLP group