Welcome to Scribd. Sign in or start your free trial to enjoy unlimited e-books, audiobooks & documents.Find out more
Download
Standard view
Full view
of .
Look up keyword or section
Like this
7Activity

Table Of Contents

0 of .
Results for:
No results containing your search query
P. 1
Computational Linguisticsms

Computational Linguisticsms

Ratings:

4.5

(1)
|Views: 234|Likes:
Published by rajappan
The success of modern software for natural language processing
impresses our imagination. Programs for orthography and grammar
correction, information retrieval from document databases, and
translation from one natural language into another, among others,
are sold worldwide in millions of copies nowadays.
However, we have to admit that such programs still lack real intelligence.
The ambitious goal of creating software for deep language
understanding and production, which would provide tools
powerful enough for fully adequate automatic translation and manmachine
communication in unrestricted natural language, has not
yet been achieved, though attempts to solve this problem already
have a history of nearly 50 years.
This suggests that in order to solve the problem, developers of
new software will need to use the methods and results of a fundamental
science, in this case linguistics, rather than the tactics of ad
hoc solutions. Neither increasing the speed of computers, nor refinement
of programming tools, nor further development of numerous
toy systems for language “understanding” in tiny domains, will
suffice to solve one of the most challenging problems of modern
science—automatic text understanding.
The success of modern software for natural language processing
impresses our imagination. Programs for orthography and grammar
correction, information retrieval from document databases, and
translation from one natural language into another, among others,
are sold worldwide in millions of copies nowadays.
However, we have to admit that such programs still lack real intelligence.
The ambitious goal of creating software for deep language
understanding and production, which would provide tools
powerful enough for fully adequate automatic translation and manmachine
communication in unrestricted natural language, has not
yet been achieved, though attempts to solve this problem already
have a history of nearly 50 years.
This suggests that in order to solve the problem, developers of
new software will need to use the methods and results of a fundamental
science, in this case linguistics, rather than the tactics of ad
hoc solutions. Neither increasing the speed of computers, nor refinement
of programming tools, nor further development of numerous
toy systems for language “understanding” in tiny domains, will
suffice to solve one of the most challenging problems of modern
science—automatic text understanding.

More info:

Published by: rajappan on Aug 06, 2008
Copyright:Attribution Non-commercial

Availability:

Read on Scribd mobile: iPhone, iPad and Android.
download as PDF, TXT or read online from Scribd
See more
See less

10/15/2011

pdf

text

original

 
CIENCIA DE LA COMPUTACIÓN
 _________________________________________________________ 
COMPUTATIONAL LINGUISTICSModels, Resources, Applications

Activity (7)

You've already reviewed this. Edit your review.
1 hundred reads
1 thousand reads
Ana Rodrigues liked this
genjin liked this
deoljagtar liked this
gjohnson7109 liked this
gzaly liked this

You're Reading a Free Preview

Download
scribd
/*********** DO NOT ALTER ANYTHING BELOW THIS LINE ! ************/ var s_code=s.t();if(s_code)document.write(s_code)//-->