Creation and Exploitation of Annotated Language Resources in Information Extraction Cross-Lingual Applications

Once upon a time, there was a series of summer schools and its name was Eurolan. It would happen in the far away land of Romania, during its long hot summer days. And among the schools of this series, the most famous of all was Eurolan 2001. Never before had the ancient city of Iasi seen such a gathering of kings and queens, of princes and princesses with only one thing in mind: to talk about the state-of-the art in the theory, methodology, and technology for creating and using annotated language resources for language engineering.

     Topics:

• • Sub-syntactic annotation (tokenization, part of speech tagging, shallow-parsing – chunking)
  • Qualitative and quantitative approaches to analysis of corpora
  • Annotation of syntax (tree banks)
  • Annotation of semantics, word sense disambiguation, semantic roles of verbs, meaning relationships, linguistic chains
  • Annotation of discourse (structure, co-reference, deep understanding)
  • Exploitation for anaphora resolution
  • Exploitation for information extraction and information retrieval
  • Exploitation for summarization, discourse interpretation and data mining
  • Exploitation for machine translation
  • Creation and exploitation tools in cross-lingual application

   

  Committee:

  Dan Cristea
  Nancy Ide
  Daniel Marcu
  Laurent Romary
  Dan Tufiș
  Sabin-Corneliu Buraga
  Gabriela Dima
  Amalia Todirascu

   

  Organizers:

  Romanian Academy, by the Institute for Artificial Intelligence “Mihai Drăgănescu” Bucharest (RACAI) and the Institute of Computer Science, Iași branch (ARFI-IIT)
  “Alexandru Ioan Cuza” University of Iași, by the Faculty of Computer Science (UAIC-FII)
  Romanian Association of Computational Linguistics (ARLC)
  University of Southern California
  The event will run under the auspices of the Technical Sciences Academy of Romania.