Multilingual multiinstitutional distant learning Example of an international

  • Slides: 9
Download presentation
Multi-lingual & multiinstitutional distant learning Example of an international master programme in Computational Linguistics

Multi-lingual & multiinstitutional distant learning Example of an international master programme in Computational Linguistics 14 -16 November, Blaubeuren, Germany Nikolai Vazov Sofia University 14 -16 November 2003 Kiril Simov Petya Ossenova LML - BAS Sofia University Bul. Tree. Bank project Mi. LCA Symposium, Blaubeuren, Germany

General goals of the programme • to put together linguistics (linguists) and computer technologies

General goals of the programme • to put together linguistics (linguists) and computer technologies (computer scientists) • to put together foreign and local expertise • to promote international multi-lingual cooperation in order to develop multilingual language electronic resources 14 -16 November 2003 Mi. LCA Symposium, Blaubeuren, Germany 2

Programme participants (1 -2 year) • Two project managment partners – French Ministry of

Programme participants (1 -2 year) • Two project managment partners – French Ministry of Foreign Affairs – French Cultural Institute in Sofia • Two academic partners – University of Sofia (2 departments) – University of Paris IV - Sorbonne 14 -16 November 2003 Mi. LCA Symposium, Blaubeuren, Germany 3

Programme participants (3 year) • Three project managment partners – French Ministry of Foreign

Programme participants (3 year) • Three project managment partners – French Ministry of Foreign Affairs – French Cultural Institute in Sofia – Agence Universitaire de la Francophonie • Six academic partners – University of Sofia (3 departments) – University of Paris IV - Sorbonne – LML - Bulgarian Academy of Sciences – University of Montréal (RALI & OLST) – University of Iaşi (Romania) – RACAI (Romania) 14 -16 November 2003 Mi. LCA Symposium, Blaubeuren, Germany 4

Organisation (educational activities) • Foreign participants – 1 -3 intensive teaching sessions – distant

Organisation (educational activities) • Foreign participants – 1 -3 intensive teaching sessions – distant follow up between the sessions – distant examination • Local participants – successive modules (1 -3 weeks each) accompanied by web-based courses – distant tutorship after the course - individual work with students (the format 8 students/15 professors allows for it) – on-line personal library for each student (articles to read and discuss with the other participants) – distant examination 14 -16 November 2003 Mi. LCA Symposium, Blaubeuren, Germany 5

Organisation (research activities) Carried out as individual tasks with twofold impact: • development of

Organisation (research activities) Carried out as individual tasks with twofold impact: • development of personal skills in manipulating electronic text data (using CLa. RK, Perl, My. SQL, XML, HTML) • integration of individual tasks into the main goal of the team - creation of mono- and multi-lingual electronic resources 14 -16 November 2003 Mi. LCA Symposium, Blaubeuren, Germany 6

Organisation (research activities) Examples: • writing tokenizers for French (solved in Tree. Tagger) •

Organisation (research activities) Examples: • writing tokenizers for French (solved in Tree. Tagger) • sentence boundaries identification (not entirely handled by Tree. Tagger, but indispensable for parallel corpora) • named entity recognition • temporal expression extraction • abbreviations identification • parenthetic expressions identification • concordances (Bulgarian & French) 14 -16 November 2003 Mi. LCA Symposium, Blaubeuren, Germany 7

On-line ressources and tools Developed by the team • CLa. RK system • Morphological

On-line ressources and tools Developed by the team • CLa. RK system • Morphological dictionary for Bulgarian • Large tagged corpus of Bulgarian • Concordances (French, Bulgarian) • Temporal expressions extractor (French) • Large archive of bilingual (French-Bulgarian) texts 14 -16 November 2003 Other available ressources • Large tagged corpus FRANTEXT • Large bilingual (French. English) aligned corpus Hansard • Taggers (Tree. Tagger and LATL) • Le Monde sur CD-ROM (with integrated search engine) Mi. LCA Symposium, Blaubeuren, Germany 8

Future work • New (better targeted) master « Electronic language resources » • Goals

Future work • New (better targeted) master « Electronic language resources » • Goals of the master defined the other way around: research needs determine the course content and not vice versa • Envisaged product: parallel French-Bulgarian corpus with named entity identification • So far: collection of parallel texts, development of proper names transcription module 14 -16 November 2003 Mi. LCA Symposium, Blaubeuren, Germany 9

ROOM ACOUSTICS II EXAMPLE PROBLEM EXAMPLE EXAMPLE EXAMPLEROOM ACOUSTICS II EXAMPLE PROBLEM EXAMPLE EXAMPLE EXAMPLE
Example 1 Example 2 Example 3 Example 4Example 1 Example 2 Example 3 Example 4
DECISION TREE Example Example DECISION TREE Example ExampleDECISION TREE Example Example DECISION TREE Example Example
Deadlocks Example 1 Example 2 Example 2 ExampleDeadlocks Example 1 Example 2 Example 2 Example
Objectives Example 1 Example 2 Example 3 ExampleObjectives Example 1 Example 2 Example 3 Example
e Health services Multilingual challenges Workshop on multilinguale Health services Multilingual challenges Workshop on multilingual
MULTILINGUAL CLASS ROOM THEORETICAL UNDERSTANDING OF MULTILINGUALISM MULTILINGUALMULTILINGUAL CLASS ROOM THEORETICAL UNDERSTANDING OF MULTILINGUALISM MULTILINGUAL
Multilingual World Wide Science Accelerating Discovery through MultilingualMultilingual World Wide Science Accelerating Discovery through Multilingual