Exciting new developments in the field of language technology

28.09.2020

We recently visited the European Language Resources Coordination (ELRC) to learn about exciting advances in language technology research, solutions and applications.

if you’re interested in languages and technology, the following links are worth a read.

https://keeleressursid.ee/et/eesti-keeleressursside-keskus The Centre of Estonian Language Resources makes digital Estonian language resources and technologies (software, dictionaries, text and speech databases, language databases) available for researchers as well as for anyone else with an interest in the field.

https://keeleressursid.ee/et/keeleressursid/konetootlusvahendid https://keeleressursid.ee/et/keeleressursid/tekstitootlusvahendid

Major strides are finally being made in the field of speech-to-text and text-to-speech in Estonian. Visit http://bark.phon.ioc.ee/ and https://www.eki.ee/heli/

Both speech-to-text and text-to-speech are a great help for the visually and hearing impaired. An example of Estonian-language subtitles converted to speech: https://www.eki.ee/heli/images/koduleht/isa_brown.mp4

A website called the Voice Recording Browser has a selection of transcriptions, such as Vikerraadio’s news program from the day before or Kuku Raadio’s midday talk show http://bark.phon.ioc.ee/tsab/p/index

As translators, we find the Institute of the Estonian Language’s databases of terminology for professional use https://term.eki.ee/termbases/index/ to be a useful resource and it is also fascinating to try out the latest neural net translation capabilities at http://neurotolge.ee/ , https://live.xn--neurotlge-v7a.ee/ and https://www.translate2018.eu/#/text

A few more sophisticated solutions:

https://metashare.ut.ee/ META-SHARE is an open, integrated, secure and interoperable sharing and exchange facility for LRs (datasets and tools) for the Human Language Technologies domain and other applicative domains where language plays a critical role;
https://www.texta.ee/ TEXTA makes your company’s document archive searchable and the information easy to manage.

And just for fun, here are a couple computer-based language games: https://keeleressursid.ee/et/keelemangud

Sources: The respective websites and A&A Lingua participants’ notes from the ELRC seminar, 3 October 2018