Content deleted Content added
Merged entry with that of "computational linguistics" |
m took a lot of text from computational linguistics for this one |
||
Line 1:
<b>Natural Language Processing</b> was/is a subfield of [[Artificial Intelligence]]. It studies the problems inherent in the processing and manipulation of natural language, but not, generally, [[Natural Language Understanding|understanding]]. It should not be confused with [[Computational Linguistics]], which is in the ___domain of [[Linguistics]].
The major tasks in <b>NLP</b> are:
* [[Text to Speech]]
* [[Speech Recognition]]
* [[Natural Language Generation]]
* [[Machine Translation]]
Some problems which make <b>NLP</b> difficult:
; [[Word boundary detection]] : In spoken language, there are no gaps between words; where to place the word boundary often depends on what choice makes the most sense gramatically and given the context.
; [[Word sense disambiguation]] : Any given word can have several different meanings; we have to select the meaning which makes the most sense in context.
; [[Syntactic ambiguity]] : The [[grammar]] for [[natural language]]s is not [[unambiguous grammar|unambiguous]], i.e. there are often multiple possible parse trees for a given sentence. Choosing the correct one usually requires [[semantics|semantic]] and contextually information.
; [[Speech acts]] and plans : Sentences often don't mean what they literally mean; for instance the correct answer to "Can you pass the salt?" is to pass the salt, not say "yes". Or again, if a class was not offered last year, the correct answer to the question "How many students failed the class last year?" is "The class was not offered last year", not "None".
| |||