Outline I. Introduction
II. Definition of CL
III. Origins
VI. Areas of Application
V. Approaches in CL
IV. Conclusion
The Association for Computational linguistics defines CL as
the scientific study of language from a computational perspective. Computational linguists are interested in providing computational models of various kinds of linguistic phenomena.
Work in computational linguistics is in some cases motivated from a scientific perspective in that one is trying to provide a computational explanation for a particular linguistic or psycholinguistic phenomenon.
II. Definition of CL
Computational linguistics is the application of linguistic theories and computational techniques to problems of natural language processing.
Grishman (1986) defines Computational linguistics as the study of computer systems for understanding and generating natural language.
The purpose of CL is to develop applications that deal with computer tasks realted to human language, like development of software for grammar correction, word sense disembiguation, compilation of dictionaries and corpora, automatic translation from one language to another, etc.
III.origins Computational linguistics originated in the
United States in the 1950s to use computers to automatically translate texts from foreign languages, particularly Russian scientific journals into English. CL was born as the name of the new field of study devoted to developing algorithms and software for intelligently processing language data.
Computers were first used for automatic/ mechanical translation.Then, their use was extended to deal with linguistics.
In order to translate a text, it was observed that one had to understand the grammar of both languages, including morphology, syntax, semantic, pragmatics, ..etc. One of the earliest and best known examples of a computer program is the s-called the ELIZA program developed by Joseph Weizenbaumat in 1966.
VI. Approaches in CL Rule-Based Systems
Explicit encoding of linguistic knowledge
Usually consisting of a set of hand-crafted,
grammatical rules
Require considerable human effort
Often fail to reach sufficient domain coverage
Data-Driven Systems
Implicit encoding of linguistic knowledge
Often using statistical methods or machine learning
methods
Require less human effort
Are data-driven and require large-scale data source
V. Application Areas
machine translationspeech recognitionman-machine interfacesintelligent word processing: spelling
correction,grammar correction
document management
find relevant documents in collections
catch plagiarism
extract information from documents
classify documents
summarize documents
summarize document collections
Conclusion
Nowdays research within the scope of CL is done at computational linguistics departments, CL laboratories, computer science departments, and linguistics departments.