EnglishLithuanianEnglish Lexicon Database Management System for MT

1
English-Lithuanian-English Lexicon Database
Management System for MT

• Gintaras Barisevicius and Elvinas Cernys

Singleton Labs.
Kaunas University of Technology, Department of
Software Engineering
2
Situation in Lithuania
3
Situation in Lithuania

• General electronic dictionaries
• http//www.fotonija.lt http//www.led.lt
• Morphological analysis tools
• Text corpora (100 mln. words)
• http//donelaitis.vdu.lt
• Speech recognition systems
• Machine translation research

4
Previous dictionary

• Open to the user dictionary
• Rigid dictionary structure
• Lack of attributes
• Not all parts of speech included
• Indexed files for dictionary storage
• Polysemy not included
• Phrases not included

5
Requirement to new system

• Open to the user dictionary
• Easy management of the attributes
• All parts of speech
• Big volume storage
• Solution to polysemy and synonyms

6
Project size
7
Current system

• Orientated to MT
• More attributes, easy to extend
• All parts of speech included
• Database for dictionary storage
• Polysemous words, domains
• Automatic generation of morphological forms
• System can work on various OS.

8
Development process

• From C to Java
• Rational Rose tool
• CVS for version control management
• MySql database

9
Adding new languages
10
System deployment localy
11
System deployment online
12
Future ambitions

• Phrases
• Text corpora
• Syntax rule realization
• Additional features
• Possible other translation choices
• WEB translation
• Video subtitle translation

13
Text corpora usage in MT

• The pen is on the table.

PEN
RASIKLIS
RASIKLIS usage with STALAS is more often!
Look usage with RASIKLIS
STALAS
TABLE
LENTELE
Look usage with RASIKLIS
14
Conclusions

• Thorough analysis of Lithuanian and English
  language conducted
• Additional features to the dictionary have to be
  added (phrases, syntax rules)
• Filling the dictionary can be started
• Machine translation is underway

15
Thank you for your attention.
Gintaras Barisevicius gintaras.barisevicius_at_stud.k
tu.lt gintaras.barisevicius_at_singleton-labs.lt