Language Resources and Tools Hackathon

September 27, Thursday

LRT Hackathon was a unique opportunity to meet developers of language tools and resources, discuss implementation and encoding details and take part in live demonstrations. Each resource indicated below was represented with a poster.
9:30 - 12:00 Anna Andrzejczuk: Wiktoria – A Polish onomasiological dictionary Renata Bronikowska i Magdalena Majdak: Słownik języka polskiego XVII i 1. poł. XVIII wieku (The dictionary of Polish of the 17th century and the first half of the 18th century – poster in Polish) Maciej Buczek: Corpora as graph databases Monika Czerepowicka: SEJF – Electronic Dictionary of Polish Multi-Word Units Łukasz Degórski: Freely distributable subcorpora of the National Corpus of Polish (NKJP) Łukasz Kobyliński: Learning from the Linguists: Combining Annotation Tools and Machine Learning Piotr Pęzik, Łukasz Dróżdż: PELCRA parallel and spoken corpora Łukasz Szałkiewicz: Corpus of the frequency dictionary of contemporary Polish (1963-67) – new annotation Jan Szejko: Lexeme Forge – a web application for creating inflection dictionaries Aleksandra Wieczorek: Proper name resources Marcin Woliński: PoliMorf Marcin Zając: Distant supervision learning of DBPedia relations
15:30 - 18:00 Mateusz Kopeć, Maciej Ogrodniczuk: LRT for Polish coreference annotation and resolution Michał Lenart, Maciej Ogrodniczuk: Web Service integration platform for Polish linguistic resources Małgorzata Majewska, Mateusz Żółtak: Digital version of the Vilnius Dictionary Bartłomiej Nitoń, Filip Skwarski: A tool for creating a Polish Valence Dictionary Maciej Ogrodniczuk, Michał Lenart: Polish Sejm Corpus Agnieszka Patejuk, Adam Przepiórkowski: Polish LFG Grammar Adam Przepiórkowski, Aleksander Buczyński, Bartosz Zaborowski: Spejd Ewa Rudnicka, Marek Maziarz, Maciej Piasecki: Mapping plWordNet onto Princeton WordNet Filip Skwarski: Polish Valence Dictionary (Walenty) Jakub Waszczuk: NERF and Constrained CRF Tagger Alina Wróblewska: Dependency parsing in Polish Bartosz Zaborowski: TaCo (tagset converter)