 |
 |
 |
 |
 |
 |
 |
|
|
|
|
|
|
|
In memory of our teacher
Prof. Dr. Georgi Gargov
 |
You will find here language data and NLP computer systems :
|
What we offer You ?
Bulgarian Grammatical Dictionary
The Bulgarian Grammatical Dictionary consists of over 60 000 lexemes of Bulgarian common language. For each word grammatical and accentological information is included. The lexical entries are classified in grammatical classes, subclasses and types. This classification describes the paradigms of synthetic wordforms and phonetic alternations. The Dictionary allows the automatic analysis and synthesis of about 900 000 wordforms.
Bulgarian Word-building Dictionary
We offer the current state of the computer model of Bulgarian word-building. This work is in progress. The model covers about 1350 morphemes at the moment. The system generates about 80 000 of the wordforms from the Bulgarian Grammatical Dictionary.
Transcription of Bulgarian Words
The system for Transcription transduces the spelling form into the corresponding correct pronunciation form.
Word stress determining system
The Word stress determining system determines the stress on any wordform included in the Bulgarian Grammatical Dictionary.
Speech Synthesis for Bulgarian
This is a very preliminary version of our system for Speech Synthesis for Bulgarian.
What's next?
The goal of our team is to process corpora on the Web using the integrated dictionaries. The tools will apply to the texts in order to locate lexical and syntactic patterns. Other goal is the integration of parallel text processing system to extract automatically bilingual terminological dictionaries.
Further tasks are a system for grammatical analysis (grammar checker) and a system for automatic translation.
Who are we?
We are a team of young researchers from the Bulgarian Academy of Sciences.
 |
Your comments are very important to us! Please send them to: gws@lml.bas.bg |
