Outline of natural language processing: Difference between revisions

Revision as of 13:31, 30 January 2021

Revision as of 07:19, 3 August 2021

Line 109:

*** [[Corpus linguistics]] – study of language as expressed in samples ''(corpora)'' of "real world" text. ''Corpora'' is the plural of ''corpus'', and a corpus is a specifically selected collection of texts (or speech segments) composed of natural language. After it is constructed (gathered or composed), a corpus is analyzed with the methods of computational linguistics to infer the meaning and context of its components (words, phrases, and sentences), and the relationships between them. Optionally, a corpus can be annotated ("tagged") with data (manually or automatically) to make the corpus easier to understand (e.g., [[part-of-speech tagging]]). This data is then applied to make sense of user input, for example, to make better (automated) guesses of what people are talking about or saying, perhaps to achieve more narrowly focused web searches, or for speech recognition.

** [[Metalinguistics]] –

** [[Sign language#Linguistics of sign|Sign linguistics]] – scientific study and analysis of natural sign languages, their features, their structure (phonology, morphology, syntax, and semantics), their acquisition (as a primary or secondary language), how they develop independently of other languages, their application in communication, their relationships to other languages (including spoken languages), and many other aspects.

* [[Human–computer interaction]] – the intersection of computer science and behavioral sciences, this field involves the study, planning, and design of the interaction between people (users) and computers. Attention to human-machine interaction is important, because poorly designed human-machine interfaces can lead to many unexpected problems. A classic example of this is the [[Three Mile Island accident]] where investigations concluded that the design of the human–machine interface was at least partially responsible for the disaster.

* [[Information retrieval]] (IR) – field concerned with storing, searching and retrieving information. It is a separate field within computer science (closer to databases), but IR relies on some NLP methods (for example, stemming). Some current research and applications seek to bridge the gap between IR and NLP.