Difference between revisions of "Natural Language Processing"

From Cyborg Anthropology
Jump to: navigation, search
 
(3 intermediate revisions by the same user not shown)
Line 1: Line 1:
 +
[[Image:natural-language-processing.jpg|center|600px]]
 
===Definition===
 
===Definition===
Natural Language Processing is a field of computer science that deals with text from human languages, both spoken and written. One common task is translating spoken words to written text. A relatively well-solved problem is part-of-speech tagging, where a computer can correctly identify the parts of speech of each word in a sentence. There are many other applications of natural language processing, including producing a summary of a block of text, optical character recognition, handwriting recognition, sentiment analysis, and machine translation.
+
Natural Language Processing is a field of computer science that deals with text from human languages, both spoken and written. A common NLP task is translating spoken words to written text, a relatively well-solved problem is part-of-speech tagging, where a computer can correctly identify the parts of speech of each word in a sentence.  
  
===Differences from Natural Language Understanding===
+
The goal of NLP is to accomplish human-like language processing. The choice of the word ‘processing’ is very deliberate, and should not be replaced with ‘understanding’<ref>Definition of Natural Language Processing. Center for Natural Language Processing. The School of Information Studies. Syracuse University. http://www.cnlp.org/publications/03nlp.lis.encyclopedia.pdf Accessed Oct 2011.</ref>. Although the field of NLP was originally referred to as Natural Language Understanding (NLU) in the early days of AI, it is well agreed today that while the goal of NLP is true NLU, that goal has not yet been accomplished. A full NLU System would be able to paraphrase an input text, translate the text into another language, answer questions about the contents of the text, and draw inferences from the text.
The word "processing" was chosen deliberately, and should not be replaced with "understanding." Understanding has other implications that are not necessary to be considered part of natural language processing.<ref>Natural Language Processing, 2. http://www.cnlp.org/publications/03nlp.lis.encyclopedia.pdf</ref>
+
  
===Goal===
+
While NLP has made serious inroads into accomplishing goals 1 to 3, the fact that NLP systems cannot, of themselves, draw inferences from text, NLU still remains the goal of NLP.<ref>Ibid.</ref> There are many other applications of natural language processing, including producing a summary of a block of text, optical character recognition, handwriting recognition, sentiment analysis, and machine translation.  
"The goal of NLP as stated above is “to accomplish human-like language processing”. The choice of the word ‘processing’ is very deliberate, and should not be replaced with ‘understanding’. For although the field of NLP was originally referred to as Natural Language Understanding (NLU) in the early days of AI, it is well agreed today that while the goal of NLP is true NLU, that goal has not yet been accomplished. A full NLU System would be able to:
+
#Paraphrase an input text.
+
#Translate the text into another language.
+
#Answer questions about the contents of the text.
+
#Draw inferences from the text.
+
While NLP has made serious inroads into accomplishing goals 1 to 3, the fact that NLP systems cannot, of themselves, draw inferences from text, NLU still remains the goal of NLP.<ref>Natural Language Processing, 2. http://www.cnlp.org/publications/03nlp.lis.encyclopedia.pdf</ref>
+
 
+
===Related Reading===
+
*[[Machine Learning]]
+
*[[Artificial Intelligence]]
+
*[[Computational Linguistics]]
+
 
+
===External Links===
+
*Lecture - 39 Natural Language Processing - I http://www.youtube.com/watch?v=bDPULOFFlaI
+
*Natural Language Processing. Liddy, E. D. In Encyclopedia of Library and Information Science, 2nd Ed. Marcel Decker, Inc. http://www.cnlp.org/publications/03nlp.lis.encyclopedia.pdf
+
*Natural Language: Understanding & Generating Text & Speech. http://www.aaai.org/AITopics/pmwiki/pmwiki.php/AITopics/NaturalLanguage
+
*Natural Language Processing Research Group at the University of Sheffield Department of Computer Science http://nlp.shef.ac.uk/
+
*What is Computational Linguistics? Hans Uszkoreit, CL Department, University of the Saarland, Germany. 2000. A short, non-technical overview of this exciting field. http://www.coli.uni-saarland.de/~hansu/what_is_cl.html
+
*The Redmond-based Natural Language Processing group http://research.microsoft.com/en-us/groups/nlp/
+
*The Stanford NLP Group http://nlp.stanford.edu/
+
*http://www.cnlp.org/publications/03nlp.lis.encyclopedia.pdf
+
  
 
==References==
 
==References==
Line 32: Line 11:
  
 
[[Category:Book Pages]]
 
[[Category:Book Pages]]
[[Category:Marked for Editing]]
+
[[Category:Finished]]
 +
[[Category:Illustrated]]
  
 
__NOTOC__
 
__NOTOC__

Latest revision as of 08:02, 18 December 2011

Natural-language-processing.jpg

Definition

Natural Language Processing is a field of computer science that deals with text from human languages, both spoken and written. A common NLP task is translating spoken words to written text, a relatively well-solved problem is part-of-speech tagging, where a computer can correctly identify the parts of speech of each word in a sentence.

The goal of NLP is to accomplish human-like language processing. The choice of the word ‘processing’ is very deliberate, and should not be replaced with ‘understanding’[1]. Although the field of NLP was originally referred to as Natural Language Understanding (NLU) in the early days of AI, it is well agreed today that while the goal of NLP is true NLU, that goal has not yet been accomplished. A full NLU System would be able to paraphrase an input text, translate the text into another language, answer questions about the contents of the text, and draw inferences from the text.

While NLP has made serious inroads into accomplishing goals 1 to 3, the fact that NLP systems cannot, of themselves, draw inferences from text, NLU still remains the goal of NLP.[2] There are many other applications of natural language processing, including producing a summary of a block of text, optical character recognition, handwriting recognition, sentiment analysis, and machine translation.

References

  1. Definition of Natural Language Processing. Center for Natural Language Processing. The School of Information Studies. Syracuse University. http://www.cnlp.org/publications/03nlp.lis.encyclopedia.pdf Accessed Oct 2011.
  2. Ibid.