New Methods, Current Trends and Software Infrastructure for NLP

TL;DR

This paper reviews current NLP trends, discusses software infrastructure needs, and introduces GATE, a versatile system supporting research and development in information extraction and other NLP applications.

Contribution

It presents GATE, a comprehensive, freely-available software framework designed to support NLP research, development, and information extraction tasks.

Findings

GATE meets key software support requirements for NLP research.

An IE system based on GATE is available for research use.

The paper reviews significant trends and related work in NLP.

Abstract

The increasing use of `new methods' in NLP, which the NeMLaP conference series exemplifies, occurs in the context of a wider shift in the nature and concerns of the discipline. This paper begins with a short review of this context and significant trends in the field. The review motivates and leads to a set of requirements for support software of general utility for NLP research and development workers. A freely-available system designed to meet these requirements is described (called GATE - a General Architecture for Text Engineering). Information Extraction (IE), in the sense defined by the Message Understanding Conferences (ARPA \cite{Arp95}), is an NLP application in which many of the new methods have found a home (Hobbs \cite{Hob93}; Jacobs ed. \cite{Jac92}). An IE system based on GATE is also available for research purposes, and this is described. Lastly we review related work.