Natural Language Processing - Villanova University

blabbingunequaledΤεχνίτη Νοημοσύνη και Ρομποτική

24 Οκτ 2013 (πριν από 3 χρόνια και 11 μήνες)

93 εμφανίσεις

Research Topics

Natural Language Processing

Image Processing

CSC 3990

Natural Language Processing

CSC 3990

What is NLP?


Natural Language Processing (NLP)


Computers use (analyze, understand,
generate) natural language


A somewhat applied field


Computational Linguistics (CL)


Computational aspects of the human
language faculty


More theoretical

Why Study NLP?


Human language interesting & challenging


NLP offers insights into language


Language is the medium of the web


Interdisciplinary: Ling, CS, psych, math


Help in communication


With computers (ASR, TTS)


With other humans (MT)


Ambitious yet practical

Goals of NLP


Scientific Goal


Identify the computational machinery
needed for an agent to exhibit various
forms of linguistic behavior


Engineering Goal


Design, implement, and test systems
that process natural languages for
practical applications

Applications


speech processing
:
get flight information or book
a hotel over the phone


information extraction
:
discover names of people
and events they participate in, from a document


machine translation
:
translate a document from
one human language into another


question answering
:
find answers to natural
language questions in a text collection or
database


summarization
:
generate a short biography of
Noam Chomsky from one or more news articles

General Themes


Ambiguity of Language


Language as a formal system


Computation with human language


Rule
-
based vs. Statistical Methods


The need for efficiency

Topic Ideas

1.
Text to Speech


artificial voices

2.
Speech Recognition
-

understanding

3.
Textual Analysis


readability

4.
Plagiarism Detection


candidate selection

5.
Intelligent Agents


machine interaction

Text to Speech


artificial voice


Text Input


Break text into phonemes


Match phonemes to voice elements


Concatenate voice elements


Manipulate pitch and spacing


Output results


Research question: How can a human voice be
used to produce an artificial voice?


Model Talker
-

opportunities for active, hands
-
on
research
(
http://www.modeltalker.com
)

Speech Recognition


Spoken Input


Identify words and phonemes in speech


Generate text for recognized word parts


Concatenate text elements


Perform spelling, grammar and context checking


Output results


Research question: How can speech recognition
assist a deaf student taking notes in class?


VUST


Villanova University Speech Transcriber
(
http://www.csc.villanova.edu/~tway/publications/wayAT08.pdf
)

Textual Analysis
-

Readability


Text Input


Analyze text & estimate “readability”


Grade level of writing


Consistency of writing


Appropriateness for certain educ. level


Output results


Research question: How can computer
analyze text and measure readability?


Opportunities for hands
-
on research

Plagiarism Detection


Text Input


Analyze text & locate “candidates”


Find one or more passages that might be plagiarized


Algorithm tries to do what a teacher does


Search on Internet for candidate matches


Output results


Research question: What algorithms work like
humans when finding plagiarism?


Experimental CS research

Intelligent Agents


Example: ELIZA


AIML: Artificial Intelligence Modeling Lang.


Human types something


Computer parses, “understands”, and generates
response


Response is viewed by human


Research question: How can computers
“understand” and “generate” human writing?


Also good area for experimentation

Image Processing

CSC 3990




Some slides from Xin Li lecture notes, West Virginia Univ.

What is Image Processing?


Digital Image Processing


Analog transmission in 1920


Early improvements in 1920s


Required
digital

computer (1948)


Rapid advancement since


Historical Background

Newspaper industry used
Bartlane cable picture
transmission system to send
pictures by submarine cable
between London and New
York in 1920s

The number of distinct gray
levels coded by Bartlane
system was improved from 5
to 15 by the end of 1920s

Digital Image Processing


The images in previous slides are digital
(now), but they are NOT the result of DIP


Digital Image Processing

is


Processing digital images by a digital
computer


DIP requires a digital computer and other
supporting technologies (e.g., data storage,
display and transmission)

Cool Applications

The first picture of moon
by US spacecraft
Ranger 7

on July 31, 1964 at
9:09AM EDT


Digitization


Compression


Error Recovery

Sir Godfrey N. Housefield and Prof.
Allan M. Cormack shared 1979
Nobel Prize in Medicine for the
invention of CT


Enhancement


Edges, Contrast,
Brightness, etc.


Acquisition


Digital cameras, scanners


MRI and Ultrasound imaging


Infrared and microwave imaging


Transmission


Internet, wireless communication


Display


Printers, LCD monitor, digital TV

Past 20 Years

Photography

Motion Pictures

Law Enhancement and Biometrics

Remote Sensing

Hurricane Andrew

taken by NOAA GEOS

America at night

(Nov. 27, 2000)

Thermal Images

Human body disperses

heat (red pixels)

Different colors indicate

varying temperatures

Operate in infrared frequency

Medical Diagnostics

chest

head

Operate in X
-
ray frequency

PET and Astronomy

Positron Emission Tomography

Cygnus Loop in the

constellation of Cygnus

Operate in gamma
-
ray frequency

Cartoon Pictures (Non
-
photorealistic)

Synthetic Images in Gaming

Age of Empire III

by Ensemble Studios

Virtual Reality (Photorealistic)

General Themes


Human vision is limited


Digital images contain more information
that humans perceive


Computers can use algorithms to extract
more information from digital images


Computers can acquire, manipulate,
compress, transmit and modify images

Topic Ideas

1.
Biometrics


identifying faces & retinas

2.
Target Acquisition


see a tank from space

3.
Computer Vision


detect microscopic flaws in
manufacturing

4.
Assistive Technology


convert visual images
into tactile or textual form

5.
Entertainment


remove red eye, morph faces,
digital filmmaking, movie magic

6.
Image Description


use 3D dictionary to
describe contents of 2D image