Chapter preview
The goal of having a computer understand and communicate in a human language has long been a dream of science fiction. In recent years part of this dream has become reality as scientists have developed computer programs that can understand and learn aspects of human languages, in both written and spoken form. These systems are also capable, to varying degrees, of translating between languages. The methods these programs use derive from both linguistics and computer science, and they reveal a relationship between the patterns found in human languages and in mathematical languages. These programs can sift through large online samples of everyday language (called corpora), counting how often particular forms actually occur in everyday use. This allows linguistic rules to be weighted based on such statistics, and these weights are used by the programs to identify more likely linguistic analyses of ambiguous utterances. The success of such programs also suggests that humans might learn by induction based on statistical regularities in their experience. The practical tools developed by computational linguists can be used to carry out linguistic analyses on a larger scale than ever before. Even more significantly, these tools can radically change the way we acquire and communicate information. All these factors make computational linguistics an intellectually lively, exciting, and influential area of study.
Review the options below to login to check your access.
Log in with your Cambridge Aspire website account to check access.
If you believe you should have access to this content, please contact your institutional librarian or consult our FAQ page for further information about accessing our content.