−Table des matières

Neoveille

Repérage, analyse et suivi des néologisme en corpus

Objectifs

  1. Plateforme de repérage, analyse et suivi des néologismes en corpus (LIPN)
  2. Etude des emprunts en corpus (LDI, CLILLAC-ARP, Ieda, EMPNEO)
  3. Etude de la néologie sémantique (ERTIM, LIPN, LDI)

Consortium

Embauche d'un ingénieur d'études

ToDo

  1. TAL server is not displaying Chinese nor Russian characters (DONE)
  2. Greek POS tagging web service (DONE)
    • We explore
  3. Tokenization problem for Tree Tagger (DONE)
  4. Tree tagger installation (Katia:DONE)
  5. Emmanuel will perform tests on the TAL server installation, specially of the POS tagging part (Emmanuel)
  1. IMS CWB web interface and Tree Tagger (Emmanuel, Katia, Jorge; Due date: November 13)
  2. Katia will install IMS CWB in her computer from scratch (Katia and Jorge)
  3. After a localhost connection is possible, we would index a corpus from Neoveille and test it (Katia & Jorge)
  4. Fix or reinstalls CPQ Web in the TAL Server (Katia, Jorge, Emmanuel)
  1. Redmine migration (Jorge)
  2. Gibhub for Neoveille (Jorge)
  3. Document TAL Cluster (Emmanuel)
  4. Project web site (Katia)
  5. Python migration (Katia)
  1. Which architecture for Neoveille's functional interface (Emmanuel, Jorge, Katia)

Schedule

Iteration 0: seven languages with POS tagging on IMS CWB

Scheduled date: November 5

RSS processing

POS Tagging

  1. POS Tagging in the seven language
    • Greek
    • Chinese
    • Russian
    • Portuguese
    • Polish
    • Czech
    • French
  2. POS Tagging with the RSS input

Indexing of the POS Tagging RSS output for IMS CWB

Dependency Analysis

Neoveille Web interface

Project web site

Iteration 1: seven languages with POS tagging and dependency analysis on D3 or IMS CWB

Iteration 2: neologism detection

Questions

Liens