way topics
TRANSCRIPT
-
7/29/2019 Way Topics
1/31
Research TopicsNatural Language Processing
Image Processing
CSC 3990
-
7/29/2019 Way Topics
2/31
Natural Language Processing
CSC 3990
-
7/29/2019 Way Topics
3/31
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
-
7/29/2019 Way Topics
4/31
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
-
7/29/2019 Way Topics
5/31
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
-
7/29/2019 Way Topics
6/31
Applications
speech processing: get flight information or booka 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 ordatabase
summarization: generate a short biography ofNoam Chomsky from one or more news articles
-
7/29/2019 Way Topics
7/31
General Themes
Ambiguity of Language
Language as a formal system
Computation with human language Rule-based vs. Statistical Methods
The need for efficiency
-
7/29/2019 Way Topics
8/31
Topic Ideas
1.Text to Speech artificial voices
2.Speech Recognition - understanding
3.Textual Analysis readability4.Plagiarism Detection candidate selection
5.Intelligent Agents machine interaction
-
7/29/2019 Way Topics
9/31
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)
http://www.modeltalker.com/http://www.modeltalker.com/ -
7/29/2019 Way Topics
10/31
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)
http://www.csc.villanova.edu/~tway/publications/wayAT08.pdfhttp://www.csc.villanova.edu/~tway/publications/wayAT08.pdf -
7/29/2019 Way Topics
11/31
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 computeranalyze text and measure readability?
Opportunities for hands-on research
-
7/29/2019 Way Topics
12/31
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 likehumans when finding plagiarism?
Experimental CS research
-
7/29/2019 Way Topics
13/31
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 computersunderstand and generate human writing?
Also good area for experimentation
-
7/29/2019 Way Topics
14/31
Image Processing
CSC 3990
Some slides from Xin Li lecture notes, West Virginia Univ.
-
7/29/2019 Way Topics
15/31
What is Image Processing?
Digital Image Processing
Analog transmission in 1920
Early improvements in 1920s
Required digitalcomputer (1948)
Rapid advancement since
-
7/29/2019 Way Topics
16/31
Historical Background
Newspaper industry used
Bartlane cable picture
transmission system to sendpictures by submarine cable
between London and New
York in 1920s
The number of distinct gray
levels coded by Bartlanesystem was improved from 5
to 15 by the end of 1920s
-
7/29/2019 Way Topics
17/31
Digital Image Processing
The images in previous slides are digital(now), but they are NOT the result of DIP
Digital Image Processingis
Processing digital images by a digitalcomputer
DIP requires a digital computer and other
supporting technologies (e.g., data storage,display and transmission)
-
7/29/2019 Way Topics
18/31
Cool Applications
The first picture of moon
by US spacecraftRanger 7
on July 31, 1964 at9:09AM EDT
Digitization
Compression
Error Recovery
Sir Godfrey N. Housefield and Prof.
Allan M. Cormack shared 1979
Nobel Prize in Medicine for theinvention of CT
Enhancement
Edges, Contrast,
Brightness, etc.
-
7/29/2019 Way Topics
19/31
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
-
7/29/2019 Way Topics
20/31
Photography
-
7/29/2019 Way Topics
21/31
Motion Pictures
-
7/29/2019 Way Topics
22/31
Law Enhancement and Biometrics
http://www.gait.ecs.soton.ac.uk/treadmill','treadmill_anim.gif -
7/29/2019 Way Topics
23/31
Remote Sensing
Hurricane Andrew
taken by NOAA GEOS
America at night
(Nov. 27, 2000)
-
7/29/2019 Way Topics
24/31
Thermal Images
Human body disperses
heat (red pixels)
Different colors indicate
varying temperatures
Operate in infrared frequency
-
7/29/2019 Way Topics
25/31
Medical Diagnostics
chest head
Operate in X-ray frequency
-
7/29/2019 Way Topics
26/31
PET and Astronomy
Positron Emission Tomography
Cygnus Loop in the
constellation of Cygnus
Operate in gamma-ray frequency
-
7/29/2019 Way Topics
27/31
Cartoon Pictures (Non-photorealistic)
-
7/29/2019 Way Topics
28/31
Synthetic Images in Gaming
Age of Empire IIIby Ensemble Studios
-
7/29/2019 Way Topics
29/31
Virtual Reality (Photorealistic)
-
7/29/2019 Way Topics
30/31
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
-
7/29/2019 Way Topics
31/31
Topic Ideas
1.Biometrics identifying faces & retinas
2.Target Acquisition see a tank from space
3.Computer Vision detect microscopic flaws in
manufacturing4.Assistive Technology convert visual images
into tactile or textual form
5.Entertainment remove red eye, morph faces,
digital filmmaking, movie magic6. Image Description use 3D dictionary to
describe contents of 2D image