Loading presentation...

Present Remotely

Send the link below via email or IM

Copy

Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.

DeleteCancel

Machine Translation

CIS 342
by

Casey Cleary

on 28 April 2010

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of Machine Translation

Machine Translation Google Translate and
other machine translators Team Pinkle:
Casey Cleary &
Tiffany Knapp VIDEO!! History Around for 50 years
Systran = Cold War
Candide = French-English How does it work?? Rule-based approach
Few words at a time Bayesian Rule
Probabilities
How likely the combination of words is right OCR: Optical Character Recognition is
a method that is used to translate a picture into text Google Translate Hybrid of machine and human translation
Uses a large database that information is continually added to Google Translator Toolkit Incorporates human knowledge
into the database to refine translations Google Goggles
Uses OCR
Changes text from a picture into machine text, and then uses Google Translate to translate and return the updated text. Systran Natural Approach
Linguists assist in programming process
Human-like translations Limitations Context: can cause mistranslations
Understanding - machines cannot fully understand WHAT DO WE THINK? Questions!
Full transcript