• Share
  • Email
  • Embed
  • Like
  • Save
  • Private Content
BigTM.net at MT Summit XII
 

BigTM.net at MT Summit XII

on

  • 4,365 views

 

Statistics

Views

Total Views
4,365
Views on SlideShare
3,569
Embed Views
796

Actions

Likes
1
Downloads
0
Comments
0

7 Embeds 796

http://www.translatum.gr 726
http://mozgorilla.com 52
http://www.slideshare.net 8
http://translate.googleusercontent.com 5
http://xss.yandex.net 2
http://webcache.googleusercontent.com 2
https://www.linkedin.com 1
More...

Accessibility

Categories

Upload Details

Uploaded via as Microsoft PowerPoint

Usage Rights

© All Rights Reserved

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Processing…
Post Comment
Edit your comment

    BigTM.net at MT Summit XII BigTM.net at MT Summit XII Presentation Transcript

    • BIGTM.NETGaining a Head Start on Translation Projects
      Achim Ruopp
      Digital Silk Road
      achim@digitalsilkroad.net
    • A New Translation Project
      “The Bundle Crusher is a sturdy machine with moving parts driven by electric motors, pneumatics, and hydraulics.”
      “The downstream platen of the compression bridge may move side-to-side unexpectedly and strike personnel in its path.”
    • A New Translation ProjectBi-Lingual Terminology
      Criteria
      In domain
      Correct
      Current
      In context
      Sources
      Translation memory from previous projects
      Domain dictionaries
    • BigTM.net Custom Translation Search
      What is it?
      Custom Translation Search Engine
      Input: project source text
      Searches the web for similar bi-lingual pages
      Indexes discovered bi-lingual pages
      Provides search UI
      Automated search and indexing overnight
      Current Language Pairs
      English - French / Italian / German / Spanish
    • BigTM.net Project Page
    • BigTM.net Search Results
    • Terminology Criteria
      Don’t find as many examples as possible – Find the right examples
    • Privacy
      Never shared
      Source text
      Customized index
      Terms
      Dictionary
      User management built-in
      Grant/revoke rights for translators
      Public: General Index of found pages
      No association to projects possible
    • BigTM.net Architecture
      SourceText
      SearchEngine
      BigTM.net
      Extracted Terms
      Candidate Pairs
      Parallel Content
      Search Index
      The Web
      Search UI
    • BigTM.net Data Flow
      Matcher
      Searchable Index
      Classifier
      MT System
      CAT Tool
      Aligner
    • Pilot Project Statistics
    • Integration with Translation Tools
      Tools with web search integration
      Dictionary download
      CSV format with probabilities
      Translation memory download
      Standard TMX format
      Open Issues
      IP (BigTM.net respects robots.txt)
      Most efficient segmentation - sub-segment matching?
    • Training of domain-specific statistical MT systems
      Supplement general domain corpus with domain-specific corpus downloaded from BigTM.net
      KDE documentation prototype English-German
    • Benefits Summary
      Automatically searches the web for similar bi-lingual pages
      Provides a searchable index
      Rapidly prototypes terminology
      Provides a core translation memory
      Training of domain-specific machine translation systems
    • Beta coming soon!
      Website: http://www.bigtm.net/
      Email: bigtm@digitalsilkroad.net
      Email your source text to get added to the beta program
      Limited Beta starting September 15th