Skip to main content

Estonia

Tour de CLARIN: Interview with Marin Laak

Tour de CLARIN highlights prominent User Involvement (UI) activities of a particular CLARIN national consortium. This time the focus is on Estonia and Marin Laak, a senior researcher and principal investigator of the Estonian Literary Museum.

Keeleveeb Query

Keeleveeb multiple dictionary and corpora query is a project initiated by an Estonian language technology company "Filosoft". Although there are several online Estonian dictionaries, both monolingual and bilingual, they are sometimes difficult to find and their simultaneous use is definitely complicated. The idea behind "keeleveeb" (it translates "language web" in English) is to carry out a query over many language resources — dictionaries and corpora.

Estonian is a moprhologically rich language, and to find a word in corpus text is not a trivial task, most propably the word that one is interested in, is in some inflected form, that is not the dictionary keyword form (singular nominative for nouns and supine for verbs). Thatswhy morphological analyser and synthesizer are integrated into the system as well.

The user interface is in Estonian, English and Russian, query can be not only for Estonian, but for other languages in the dictionaries as well (eg. English, Russian, Finnish, German).

For more information, relevant datasets, tools and online services, please visit http://www.keeleveeb.ee.

The keeleveeb.ee service is useful for (but use is not limited to):

  • translators,
  • language learners,
  • teachers,
  • students,
  • schoolchildren
  • terminologists in different fields
Project leader
Neeme Kahusk
Contact email
Acknowledgements

Filosoft (http://www.filosoft.ee)

Rene Prillop (main developer: prr [at] filosoft.ee (prr[at]filosoft[dot]ee))

Heiki-Jaan Kaalep

Tarmo Vaino

National Programme for Estonian Language Technology

EKRM (Eesti keel ja rahvuslik mälu)

Creators of Free Dictionaries

Web hosting: EENet (up to 2013), CELR (from 2013)