What is
computational linguistics?
The scientific goal
of computational linguistics is to understand the acquisition, comprehension
and production of human languages in information processing terms. Because
language is used to convey information we assume that these processes
fundamentally involve the processing of information, i.e., that they
are fundamentally computational in nature. Computational linguistics
also has a more applied, technological side: if we understand the information
processing involved in human language, we can also implement it on computers.
Applications of computational linguistics include:
- Machine translation (i.e., translating
documents from one language to another by computer)
- Speech recognition (e.g., transcribing
speech)
- Information extraction (e.g., automatically
identifying the topic of a document, the things that it talks about,
and the important relationships between those things)
Even after the dot.com bubble, there is
a steadily increasing demand for people with training in computational
linguistics in the software industry.
Specializing in computational linguistics
at Brown
There is no separate concentration in
Computational Linguistics; students who wish to specialize in Computational
linguistics typically concentrate in Cognitive Science, Computer Science
or Linguistics (double majoring in Computer Science and Linguistics
is very common).
There are two courses that every student
intending to specialize in Computational Linguistics should take (they
do not have to be taken in order).
Students specializing in computational
linguistics should have a reasonable background in linguistic theory,
especially natural language syntax and semantics.
- CG131 Introduction to Syntax
- CG113 Introduction to Formal Semantics
Computational skills are of course very
useful for computational linguistics. In addition to programming courses,
relevant courses include:
- CS22 Introduction to Discrete Mathematics
- CS51 Models of Computation
- CS141 Introduction to Artificial
Intelligence
- CS181 Computational Molecular Biology
(it turns out that computational linguistics techniques also get
applied here)
- CS295:3 Machine Learning and Pattern
Recognition
Finally, statistical methods are now absolutely
essential for modern computational linguistics. We are lucky to have
several statisticans here at Brown who specialize in stochastic grammars
and other kinds of models of sequences. The following courses are highly
recommended for anyone specializing in computational linguistics.
- AM165/166 Statistical Inference
(the basic course)
- AM169 Computational Probability
and Statistics
- AM171 Information theory
|
