In this second article about the explanations of some of the topics that deal with Human Language Technologies, I’ll focus on another area where the Language Technology Group conducts research: Machine Learning.

   As an introduction we can mention what Wikipedia points out about this topic. Machine learning is a subfield of artificial intelligence that is concerned with the design and development of algorithms and techniques that in some way make the computers learn. As Martin Sewell mentions, in practice, this involves creating programs that optimize a performance criterion through the analysis of data. The major focus of machine learning research is to extract information from data automatically, by computational and statistical methods. Hence, machine learning is closely related not only to data mining and statistics, but also theoretical computer science. Among all the applications that machine learning has, wikipedia mentions the following: natural language processing, syntactic pattern recognition, search engines, medical diagnosis, bioinformatics and cheminformatics, detecting credit card fraud, stock market analysis, classifying DNA sequences, speech and handwriting recognition, object recognition in computer vision, game playing and robot locomotion.

       According to Ethem Alpaydin, in machine learning the approach is to collect a large collection of sample utterances from different people and learn to map these to words. Already, there are many successful applications of machine learning in various domains: there are comercially available systems for recognizing speech and handwriting.

Machine learning is not just a database problem; it is also a part of artificial intelligence as said above. To be intelligent, a system that is in a changing environment should have the ability to learn. Machine learning also helps us find solutions to man problems in vision, speech recognition, and robotics.

Sources:

*Martin Sewell. “Machine Learning”. (2007). Retrieved 22:45, April11, 2008, from http://www.machinelearning.net/machine-learning.pdf 

*Ethem Alpaydin. “Introduction to Machine Learning”. Published in 2004, MIT Press. 415 pages. Retrieved 23:12, April 11, 2008, from http://books.google.com/books?hl=en&lr=&id=1k0_-WroiqEC&oi=fnd&pg=PR13&dq=introduction+to+machine+learning&ots=p8XJTOgLyQ&sig=o-HYojpOGv2AVM5voMAe0WHibjw

*Machine learning. (2008, April 1). In Wikipedia, The Free Encyclopedia. Retrieved 14:01, April 12, 2008, from http://en.wikipedia.org/w/index.php?title=Machine_learning&oldid=202557440