Statistical Natural Language Processing – Recap

Dr. Ng gave a terrific talk on the field of natural language processing which combines many disciplines to address pressing problems.  He also introduced many of our students to the problems they will encounter on the North American Computational Linguistics Olympiad being held at UTD.

To help participants prepare for NACLO, Dr. Ng will host a problem session this Sunday to go over selected NACLO problems. Here are the date and location of the problem session:

Date and Time: Sunday, Jan 25, 2-5 PM
Location: Room 2.201, Engineering and Computer Science South Building, University of Texas at Dallas

You may also get updated information about the local NACLO competition, as well as additional sample NACLO problems from Dr. Ng’s website: http://www.hlt.utdallas.edu/~vince/naclo

Dr. Ng has provided his slides from the lecture.  Members of the Metroplex Math Circle e-mail group can download these files from the group site. To join the e-mail group simply click below.

Click to join MetroplexMathCircle

January 17, 2009: Statistical Natural Language Processing

Please come join us for the first Metroplex Math Circle of 2009.  On January 17 we will have Dr. Vincent Ng from UT Dallas talk to us about an exciting new field of applied mathematics as well as a new Olympiad with national and international competitions.

Statistical Natural Language Processing and the North American Computational Linguistics Olympiad

Abstract:
People have long believed that technology will eventually produce a machine that can speak to us. Natural language processing (NLP), one of most fascinating subfields of artificial intelligence, is devoted to enabling computers to use human languages both as input and as output. However, more than fifty years have passed since the inception of artificial intelligence, and we still have not been able to construct such a “talking machine.” In the first part of this talk, we will examine why NLP is so difficult, and take a look at how statistics have revolutionized the way computers understand human languages.

In the second part of the talk, we will give an overview of the North American Computational Linguistics Olympiad (NACLO), an international contest that aims to stimulate high-school students’ interest in natural language processing by having them solve linguistic puzzles. A local contest will be held at the University of Texas at Dallas on February 4, 2009.   Interested high-school students can now register through the NACLO website (www.naclo.cs.cmu.edu).

Computational Linguistics

Discrete mathematics and problem solving skills can lead to a very wide variety of careers.  With the upcoming NACLO competition and a lecture on Natural Language Processing, we will profile the emerging field of Computational Linguistics.  The following description is offered by Dr. Hans Uszkoreit:

Computational linguistics (CL) is a discipline between linguistics and computer science which is concerned with the computational aspects of the human language faculty. It belongs to the cognitive sciences and overlaps with the field of artificial intelligence (AI), a branch of computer science aiming at computational models of human cognition. Computational linguistics has applied and theoretical components.

Human language is a most exciting and demanding puzzle.

Theoretical CL takes up issues in theoretical linguistics and cognitive science. It deals with formal theories about the linguistic knowledge that a human needs for generating and understanding language. Today these theories have reached a degree of complexity that can only be managed by employing computers. Computational linguists develop formal models simulating aspects of the human language faculty and implement them as computer programmes. These programmes constitute the basis for the evaluation and further development of the theories.  In addition to linguistic theories, findings from cognitive psychology play a major role in simulating linguistic competence.  Within psychology, it is mainly the area of psycholinguistics that examines the cognitive processes constituting human language use. The relevance of computational modeling for psycholinguistic research is reflected in the emergence of a new subdiscipline: computational psycholinguistics.

We teach computers to communicate with people.

Applied CL focusses on the practical outcome of modelling human language use. The methods, techniques, tools and applications in this area are often subsumed under the term language engineering or (human) language technology. Although existing CL systems are far from achieving human ability, they have numerous possible applications. The goal is to create software products that have some knowledge of human language. Such products are going to change our lives. They are urgently needed for improving human-machine interaction since the main obstacle in the interaction beween human and computer is a communication problem. Today’s computers do not understand our language but computer languages are difficult to learn and do not correspond to the structure of human thought. Even if the language the machine understands and its domain of discourse are very restricted, the use of human language can increase the acceptance of software and the productivity of its users.

NACLO 2009

Adam Hesterberg

Students who excel at math competitions like the AMC 10 and 12 might be interested in participating in the North American Computational Linguistics Olympiad coming up in February.   Similar to the USAMO, this national test is used to select a team to compete internationally in the International Linguistics Olympiad.

Like Math Circles and international problem solving competitions, these linguistics competitions have their origins in Eastern Europe.  They also appear to draw on many of the same problem solving and thinking talents of successful Math Olympians.    In this interview with Adam Hesterberg, a former MATHCOUNTS and USAMO winner, explains how he prepared for his win in last year’s ILO.

For those of us in the Metroplex area it appears that the University of North Texas in Denton will be offering the NACLO this year.