Interim Results of the HaBiT project

Outputs

The first version of HaBiT system prototype

The prototype is accessible at ​http://corpora.fi.muni.cz/habit

The system includes selected corpus processing tools and the following HaBiT corpora:

• ​Amharic WIC corpus, 200 thousand tokens

Amharic WIC corpus (News from Walta Information Center), manually tagged.

• ​Amharic WaC corpus, 17 million tokens

Amharic web corpus. Crawled by SpiderLing in August 2013 and October 2015. Encoded in UTF-8, cleaned, deduplicated. Automatically tagged by TreeTagger trained on Amharic WiC

Publications

D - conference paper, J - journal paper, R - software

• D - Vít Baisa, Jane Bradbury, Silvie Cinková, Ismaïl El Maarouf, Adam Kilgarriff, Octavian Popescu. SemEval-2015 Task 15: A CPA dictionary-entry-building task. In Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015). Denver, Colorado: Association for Computational Linguistics, 2015. s. 315-324, 10 s. ISBN 978-1-941643-40-2. ​https://is.muni.cz/auth/publication/1308719
• D - Adam Kilgarriff, Vít Baisa, Miloš Jakubíček, Pavel Rychlý. Longest-commonest Match. In Kosem, I., Jakubíček, M., Kallas, J., Krek, S.. Electronic lexicography in the 21st century: linking lexical data in the digital age. Proceedings of the eLex 2015 conference, 11-13 August 2015, Herstmonceux Castle, United Kingdom. Jlubljana: Trojina, Institute for Applied Slovene Studies, 2015. s. 397-404, 8 s. ISBN 978-961-93594-3-3. ​https://is.muni.cz/auth/publication/1308616
• D - Lucia Kocincová, Miloš Jakubíček, Vojtěch Kovář, Vít Baisa. Interactive Visualizations of Corpus Data in Sketch Engine. In Gintaré Grigonyté, Simon Clematide, Andrius Utka, Martin Volk. Proceedings of the Workshop on Innovative Corpus Query and Visualization Tools at NODALIDA 2015. Vilnius, Lithuania: Linköping University Electronic Press, Linköpings universitet, 2015. s. 17-22, 6 s. ISBN 978-91-7519-035-8. ​https://is.muni.cz/auth/publication/1299713
• D - Adam Rambousek, Aleš Horák. DEBWrite: Free Customizable Web-based Dictionary Writing System. In Kosem, I., Jakubiček, M., Kallas, J., Krek, S.. Electronic lexicography in the 21st century: linking lexical data in the digital age. Ljubljana/Brighton: Trojina, Institute for Applied Slovene Studies/Lexical Computing Ltd., 2015. s. 443-451, 9 s. ISBN 978-961-93594-3-3. ​https://is.muni.cz/auth/publication/1308365
• D - Vít Baisa, Vít Suchomel. Corpus Based Extraction of Hypernyms in Terminological Thesaurus for Land Surveying Domain. In Ninth Workshop on Recent Advances in Slavonic Natural Language Processing. Brno: Tribun EU, 2015. s. 69-74, 6 s. ISBN 978-80-263-0974-1. ​https://is.muni.cz/auth/publication/1318498
• D - Vít Baisa, Ondřej Herman, Miloš Jakubíček. Towards Automatic Finding of Word Sense Changes in Time. In Aleš Horák, Pavel Rychlý, Adam Rambousek. Ninth Workshop on Recent Advances in Slavonic Natural Language Processing. Brno: Tribun EU, 2015. s. 33-41, 9 s. ISBN 978-80-263-0974-1. ​https://is.muni.cz/auth/publication/1318600

Deliverables

• D1.1.1 System specifications: Overall system design definitions
• D1.1.2 Specification of corpora and the corpus building module
• D1.1.3 Specification of word-sketch grammars and tools
• D1.1.4 Specification of the semantic content matching and wordspace module
• D4.1: Methodology of Sketch Grammar evaluation
• D1.2.1 The HaBiT system v1: First integrated system prototype
• D6.1 Project evaluation plan