Recent basic research and development activities at CRL have concentrated on the development of methods for producing large-scale natural language processing systems using machine translation, information retrieval and extraction, text summarization, lexicon and other linguistic resource development, belief modeling, text analysis and generation as well as workbench projects for linguists and translators. Below are brief descriptions of current research projects and links to the project web sites.  

Recently completed research projects

Project Title	Description
	The goal of CRL's SAY project is to develop resources for lesser studied languages. Currently the languages being studied are: Amharic, one of the languages spoken in Ethiopia, Chechen, the language spoken by the people of Chechnya Guaraní­:, one of the languages spoken by many people in Paraguay and Argentina. Myanmar (a.k.a. Burmese) official language of Myanmar and a language spoken in Bangladesh in an area bordering Myanmar Maguindanao, one of the languages spoken by the Phillipine people. Uyghur, a language spoken in the Xinjiang province of China. For questions about this project contact Dr. Jim Cowie.
	Chemical and Biological Defense Multivariate Decision Support Tools This project aims to assist those charged with allocating research funds to make decisions that will most efficiently reduce the threat of chemical and biological attacks. A team of researchers from UNM, NMSU, Sandia and the Center for Non-Proliferation Studies are engaged on this project, including mathematicians, analysts, engineers, computer scientists, linguists, and composers. At one level, the project will use iterative modelling to gauge the effects of chemical and biological attacks on targets such as embassies, air bases, etc. and the ameliorating effects of improvements in sensors, equipment, or other technology on these attacks. At a second level, it will model the informed opinions of experts as to the resources (financial, manpower, and time) that would need to be expended to achieve these improvements in threat reduction. At yet a third level, it will explore new methods of decision making that can take into account complex interactions and dependencies between options. The resulting software, if the project is funded through to completion, would be suitable for use in many other kinds of complex decision-making tasks. For questions about this project contact Dr. Jim Cowie.
	Preparing War Fighters for Extreme Environmental Challenges This project goes beyond the research efforts conducted on the effects of one or many extreme environmental conditions (heat, cold, wind, etc.) on war fighters, and aims to determine the effects of multiple variables on an individual, as well as a team of war fighters. For questions about this project contact Dr. Jim Cowie
	AWARE - Discovering characteristics of habitable answering systems The purpose of this project is to investigate how question answering systems can best present results to a user in such a way that the user is aware of what question the system has actually answered and how it arrived at the answer. As part of this project we are investigating how users interact with MIT's START question answering system and Language Computer Corporation's Internet Answer question answering system. In addition, we are examining how people use referring expressions when interacting with natural language systems. For questions about the AWARE project contact Dr. Bill Ogden
	Computer-Mediated Multilingual Collaboration This project involves evaluation of a multilingual chat system in two dimensions: How well the users can interact with the system to accomplish their tasks; The quality of the translations produced in multilingual chats. To test for the latter case, the system was tested on English, Chinese, Japanese, Spanish, and Korean languages. For questions about this project contact Dr. Bill Ogden
	Gene Literature Exploration Environment This is a project in collaboration with the University of New Mexico Cancer Research and Treatment Center. The goal of this project is to speed up the process of searching volumes of data for help in analyzing new genetic research. For questions about this project contact Dr. Jim Cowie
	Interlingual Annotation of Multilingual Text Corpora CRL has been awarded an NSF project in collaboration with UMIACS (Univ. of Maryland, College Park), ISI (Univ. of Southern California), LTI (Carnegie-Mellon University), Columbia University, and Mitre Corporation. more .... IAMTC's Website
	Meaning Oriented Question Answering is CRL's project in collaboration with CoGenTex in Ithaca, NY, and ILIT (Institute for Language and Information Technologies) at UMBC (University of Maryland, Baltimore County). The goal of this project is to bring to bear CRL's ONTOSEM ontology and TMR (Text Meanning Representation) to enhance both the accuracy and user-friendliness of question/answering systems. For questions about the MOQA project contact Dr. Jim Cowie, or Dr. Steve Helrmeich.
Who is?	Biography Generator This project involves developing a multilingual system to generate personal biographies. Its interface allows a user to collect web documents on a specific person and automatically assemble relevant pieces of the documents into a resume of that person. Links to summaries and the original documents are maintained. Currently the system is being tested on English, Spanish and Russian languages. For questions about this project contact Dr. Jim Cowie
	Using Jargon to Identify Author's Perspective The primary objective of this research is to test the hypothesis that information in a document, called jargon, can help to identify the background opinions or beliefs of the author. The first phase of the project tests whether an author's opinion can be identified for a text that explicitly addresses an issue about which the author has an opinion. The second attempts to ... Read more ... For questions about this project contact Dr. Steve Helmreich or Dr. David Farwell

webmaster@crl.nmsu.edu

Last Modified:

October 2, 2006