| Project
Title |
Description |
| Arabic Translation System |
The Arabic Translingual Research System contains collections of
newspapers from various Arabic speaking countries. User's can retrieve
documents using either English or Arabic queries. Individual words in
the retrieved documents can be looked up in a dictionary and word for
word translation of the documents can also be carried out. |
Crest |
This project combined high-risk/high-yield research with the development
of working systems for a number of natural language applications.
The applications include:
 | machine translation, |
| crosslingual information retrieval, |
| crosslingual and cross-document information extraction, |
| summarization and |
| task-oriented combinations of the above. |
The main thrust of the research work was enhancing basic capabilities in
text processing, with the view of attaining a new level of quality for NLP
applications. The main thrust of the develop-ment work was judicious
integration of diverse methods and resources in application-oriented
systems.
|
| Expedition |
This
project was devoted to developing a computational environment for enabling and speeding up
quick ramp-up of machine translation systems for "low density" languages. |
| Corelli |
The
goal of the Corelli project was to develop a framework, architecture and tools, for rapid
deployment of multilingual machine-translation systems, with an emphasis on
machine-translation for assimilation purposes and on languages for which electronic or
human resources are scarce or difficult to obtain. |
| Mikrokosmos |
Knowledge-Based Machine Translation and comprehensive treatment of lexical, ontological, and text meanings in a "society of microtheories"
architecture.
|
| MINDS |
The
MINDS (multilingual interactive document summarization) project involved the
summarization, extraction and translation for Japanese, Spanish and Russian. |
| Oleada |
This
project was an extension to the task of language instruction of the technology, resource
base and graphical user interface design developed in the Cíbola Project. |
| Shiraz |
This project involved the creation of an extensible research prototype of a Persian to
English machine translation system that can be used to explore the requirements of future
Persian machine translation development. |
| Asian
Language Corpus Analysis and Display: Motif X Windows for Chinese and Japanese |
This
project involves the development, installation and support of Asian text processing
capabilities on Sun workstations. The basic system allows a user to display, save and edit
texts containing Chinese and Japanese characters and provides support for Asian text
processing including the development of an integrated Asian Key Word in Context (KWIC)
search capability. |
| GATE |
The GATE project (version 1.1) at CRL and the University of
Sheffield emphasized the building of large-scale natural language processing systems by
reusing natural language processing components. |
| GraphLing |
This
work involved developing probabilistic classifiers for two challenging and diverse natural
language processing tasks using a common set of techniques. |
| Pragmatics
Based Machine Translation |
The
large objectives of this research are to establish a theoretical framework for
investigating the pragmatic aspects of the translation process and to implement a
computational platform for carrying out systematic experiments on the pragmatics of
translation. |
| URSA |
The
Unicode Retrieval System Architecture (URSA) is an attempt to make detection, retrieval
and collection visualization completely transparent to query and document language issues.
Ongoing work involves prototypes of translingual or cross-language information retrieval
systems, the development of Unicode IR technologies, and close integration with the
Tipster document management architecture. |
