<!doctype html public "-//w3c//dtd html 4.0 transitional//en">
<html>
<p><font size=+2>The NMSU Computing Research Laboratory Presents</font>
<p><font size=+2>The 1999 Summer School in Language Engineering</font>
<br><font size=+2>June 28-July 9</font>
<p>The 1999 Summer School in Language Engineering is designed for the practical
computational linguist or natural language processing specialist.
<p>The program of the school stresses practical needs of application system
builders in such areas as machine translation, information retrieval and
extraction and text summarization. It stresses the broad range of multilingual
aspects of today's language engineering, from the support for the various
writing systems to acquisition of linguistic knowledge for applications
to languages that have not yet been widely studied.
<p>The summer school is organized by the Computing Research Laboratory
(CRL) of New Mexico State University. The instructors, both members of
CRL staff and visiting professors, are all leaders in their respective
areas of expertise.
<p>The school will feature two full weeks of instruction and hands-on practical
studies. The number of students in the school will be small, keeping a
high instructor-to-student ratio. Registrants will be accepted on a first-come
first-served basis. Preregistration and fees must be received no later
than June 1.
<p><b>For more information,</b>
<br><b>please visit our web site at:</b>
<br><b><a href="http://crl.nmsu.edu/summerschool">http://crl.nmsu.edu/summerschool</a></b>
<p><b><font size=+1>Course Descriptions</font></b>
<p><b>"Ecological" Issues in Language Engineering</b>
<br>This course will cover issues related to writing systems, encodings,
input and output methods; treatment of punctuation, special characters
and symbols, including mark-up; processing of dates and numbers; and a
variety of issues connected with managing large multilingual collections
of documents featuring different mark-up styles. A number of computational
tools will be introduced and used in practical exercises.
<p><b>Approaches to Computational Morphology</b>
<br>After a presentation of several approaches to computational morphology,
with example systems for such widely different languages as Spanish, Persian,
Russian and Turkish, this course will concentrate on the engineering of
state-of-the-art morphological analysis and generation systems, especially
for languages other than English. Students will get hands-on experience
using sophisticated development and testing tools, by building a morphological
analyzer.
<p><b>Lexicon Acquisition for NLP I: Morphology and Syntax</b>
<br>This course will describe the process of design and acquisition of
several types of lexicons for NLP systems: lexicons supporting morphological
and syntactic analysis of texts in a language, transfer lexicons for machine
translation and multilingual onomastica (lexicons of proper names). A number
of acquisition interfaces will be used in practical exercises.
<p><b>Lexicon Acquisition for NLP II: Ontological Semantics</b>
<br>This course will present the design and acquisition of static knowledge
sources to support analysis of meaning in natural language texts. In particular,
it will cover designing and building ontologies, or world models, for NLP
and lexicons for the support of semantic analysis of particular languages.
Practical exercises will be supported by interactive acquisition interfaces.
<p><b>Knowledge Elicitation from Informants</b>
<br>his course will present an environment for eliciting grammatical and
lexical knowledge about a language from a user who knows that language
and English but is not a trained linguist. This kind of environment is
a realistic alternative to experimenting with automatic elicitation of
language knowledge. It combines corpus-based, expectation-based and failure-driven
acquisition of declarative knowledge about a language and is most useful
for the languages for which few computational resources are available.
The design of the acquisition process and system will be discussed, and
the interface, Boas, will be used in practical exercises.
<p><b>A Survey of Language Engineering Applications</b>
<br>This course will introduce language engineering applications such as
machine translation, information retrieval and extraction, text summarization
and language instruction. The tasks and techniques learned in the other
courses will be put in their context and further illustrated. The following
systems will be presented and available for laboratory work: the Corelli
machine translation environment; the MINDS information retrieval and summarization
system, the URSA cross-language information retrieval engine, the Oleada
language instruction environment and translator's tool set, the Mikrokosmos
machine translation system and the Expedition environment for configuring
machine translation systems for low-density languages.
<br>
<p><b><a href="http://crl.nmsu.edu/summerschool">http://crl.nmsu.edu/summerschool</a></b>
<br>
<br> </html>