<?xml version="1.0" standalone="yes"?>
<Paper uid="W02-0108">
  <Title>Using GATE as an Environment for Teaching NLP</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> When students learn programming, they have the benefit of integrated development environments, which support them throughout the entire application development process: from writing the code, through testing, to documentation. In addition, these environments offer support and automation of common tasks, e.g., user interfaces can be designed easily by assembling them visually from components like menus and windows. Similarly, NLP and CL students can benefit from the existence of a graphical development environment, which allows them to get hands-on experience in every aspect of developing and evaluating language processing modules. In addition, such a tool would enable students to see clearly the practical relevance and need for language processing, by allowing them to experiment easily with building NLP-powered (Web) applications.</Paragraph>
    <Paragraph position="1"> This paper shows how an existing infrastructure for language engineering research - GATE (Cunningham et al., 2002a; Cunningham, 2002) - has been used successfully as an NLP teaching environment, in addition to being a successful vehicle for building NLP applications and reusable components (Maynard et al., 2002; Maynard et al., 2001). The key features of GATE which make it particularly suitable for teaching are: * The system is designed to separate cleanly low-level tasks such as data storage, data visualisation, location and loading of components and execution of processes from the data structures and algorithms that actually process human language. In this way, the students can concentrate on studying and/or modifying the NLP data and algorithms, while leaving the mundane tasks to GATE.</Paragraph>
    <Paragraph position="2"> July 2002, pp. 54-62. Association for Computational Linguistics. Natural Language Processing and Computational Linguistics, Philadelphia, Proceedings of the Workshop on Effective Tools and Methodologies for Teaching * Automating measurement of performance of language processing components and facilities for the creation of the annotated corpora needed for that.</Paragraph>
    <Paragraph position="3"> * Providing a baseline set of language processing components that can be extended and/or replaced by students as required.</Paragraph>
    <Paragraph position="4"> These modules typically separate clearly the linguistic data from the algorithms that use it, thus allowing teachers to present them separately and the students to adapt the modules to new domains/languages by just modifying the linguistic data.</Paragraph>
    <Paragraph position="5"> * It comes with exhaustive documentation, tutorials, and online movie demonstrations, available on its Web site (http://gate.ac.uk).</Paragraph>
    <Paragraph position="6"> GATE and its language processing modules were developed to promote robustness and scalability of NLP approaches and applications, with an emphasis on language engineering research.</Paragraph>
    <Paragraph position="7"> Therefore, NLP/LE courses based on GATE offer students the opportunity to learn from non-toy applications, running on big, realistic datasets (e.g., British National corpus or news collected by a Web crawler). This unique research/teaching duality also allows students to contribute to research projects and gain skills in embedding HLT in practical applications.</Paragraph>
  </Section>
class="xml-element"></Paper>