linking localisation and language resources
play

Linking Localisation and Language Resources Dominic Jones, David - PowerPoint PPT Presentation

Linking Localisation and Language Resources Dominic Jones, David Lewis, Alexander OConnor, Leroy Finn Post-doctoral Researcher, Knowledge & Data Engineering Group, Center for Next Generation Localisation (CNGL) Trinity College Dublin 2


  1. Linking Localisation and Language Resources Dominic Jones, David Lewis, Alexander O’Connor, Leroy Finn Post-doctoral Researcher, Knowledge & Data Engineering Group, Center for Next Generation Localisation (CNGL) Trinity College Dublin

  2. 2 Creators, consumers & the Web Addressing the challenges of dynamic user-generation content localisation.

  3. 3 Linked Localisation - Interoperability Content Access Control Provenance (LD vs. LOD) Term Bases (TB) Language Service Provider (LSP) Computer-Aided Training + Translation (CAT) retraining Translation Machine Translation (MT) Memory (TM)

  4. 4 Linked Localisation – Architecture Between, Creator, LSP and Translator Translation Visualizer Provenance CNGL Service Model CNGL Content XLIFF Model Human Translation Machine Post Translation & … Memory & Translation Editing Segmentation Term Bases

  5. 5 Motivation: Vs. http://www.tcd.ie/Library/bookofkells/ http://www.apple.com/ipad/ � CMS-LION emphasises on “ user-generated ” content providing: • The history of a piece of translation. • Revision and version control on the translation process. • Quality Assurance (QA) data on translated content. • Consensus on the translation process. • Syncronisation between all agents involved in the translation process.

  6. 6 Worked Example: English German Tweet CNGL hasSourceLang hasTargetLang ServiceModel hasCategory This is sentence 1. This is sentence 2. This is sentence 3. classOf hasContentType hasJobID plainText Machine Job1 Translation c l a s Job1_hasSentence1 s O f g n i s This is sentence 1. U CNGL d e ContentModel t a l s Job1_hasSentence2 n a r T This is sentence 2. Human Translation Das ist Satz 1. Job1_hasSentence3 This is sentence 3. TranslatedBy Dies ist Satz 1. “Dominic”

  7. 7 Provenance … The history of an artifact. � Open Provenance Vocabulary CNGL Content • Lightweight version of Open Provenance Model Model • http://open-biomed.sourceforge.net/opmv/ns.html CNGL Service Model

  8. 8 Provenance: (1) CNGL Service Model CNGL Content Model

  9. 9 Provenance: (2) CNGL Service Model CNGL Content Model

  10. 10 Future Plans … http://www.w3.org/International/multilingualweb/lt/ LD @ the ITS 2.0 LSP http://www.vistatec.com/ Test-bed ! http://www.panacea-lr.eu/ Post- Workflow Editing MT Orchestration Feedback http://www.localisation.ie/solas/

  11. 11 "A Semantic Model for Further Reading … Integrated Content Management, Localisation and Language Technology ML Processing" presented at the 2nd Workshop on Dave.Lewis@scss.tcd.ie the Multilingual (Semantic) Dominic.Jones@scss.tcd.ie Semantic Web Bonn, Leroy.Finn@scss.tcd.ie Germany, 23rd October 2011. Web MLW "Linking Localisation “Linked Data for LOD and Language Language Resource Resources" presented Lang Sharing in the Long L10n at the Linked Data in Tail of the Localisation Linguistics Workshop, Resources Market” presented at Frankfurt/Main, Language Resources Germany March 7 – 9, and Evaluation (LREC) 2012. May 2012.

Recommend


More recommend