**************************************************************
14th WORKSHOP ON BUILDING AND USING COMPARABLE CORPORA (online) In conjunction with RANLP 2021 (online) Monday, September 6, 2021 Workshop website: https://comparable.limsi.fr/bucc2021/ RANLP website: https://ranlp.org/ranlp2021 INVITED SPEAKERS * Pushpak Bhattacharyya https://www.cse.iitb.ac.in/~pb/ * Tomas Mikolov https://ricaip.eu/home/responsible-research-and-innovation-strategy/research-teams/tomas-mikolov * Sujith Ravi https://www.sravi.org/ ************************************************************** The workshop will be held on Monday, Sept. 6, 2021 using Zoom. You can still register for it on the RANLP main conference website at https://ranlp.org/ranlp2021/fees.php . The registration fee for non-presenters is 15 Euros and there is no late registration surcharge. Please find the workshop programme below. A formatted version of it will be posted on the workshop website (URL see above) by Sept. 4. The proceedings will follow by Sept. 5. ************************************************************** Programme 14th BUCC Workshop, Monday, Sept. 6, 2021 (subject to change) All times are in UTC+0 For a time zone converter and time difference calculator, see e.g. https://www.timeanddate.com/worldclock/converter.html Note that during summer time (which is applicable on Sept. 6) London is at UTC+1 8:00 - 8:05 Welcome 8:05 - 9:00 Invited presentation Machine Translation in Low Resource Setting Pushpak Bhattacharyya 9:00 - 9:25 EM Corpus: a comparable corpus for a less-resourced language pair Manipuri-English Rudali Huidrom, Yves Lepage and Khogendra Khomdram 9:25 - 9:40 Coffee break 9:40 - 10:05 Mining Bilingual Word Pairs from Comparable Corpus using Apache Spark Framework Sanjanasri JP, Vijay Krishna Menon, Soman KP andKrzysztof Wolk 10:05 - 10:30 Employing Wikipedia as a resource for Named Entity Recognition in Morphologically complex under-resourced languages Aravind Krishnan, Stefan Ziehe, Franziska Pannach and Caroline Sporleder 10:30 - 10:55 Semi-Automated Labeling of Requirement Datasets for Relation Extraction Jeremias Bohn, Jannik Fischbach, Martin Schmitt,Hinrich Schütze and Andreas Vogelsang 10:55 - 11:20 A Dutch Dataset for Cross-lingual Multilabel Toxicity Detection Ben Burtenshaw and Mike Kestemont 11:20 - 12:10 Lunch break 12:10 - 13:05 Invited presentation Topic: Language modeling and AI Tomas Mikolov 13:05 - 13:30 Syntax-aware Transformers for Neural Machine Translation: The Case of Text to Sign Gloss Translation Santiago Egea Gómez, Euan McGill and Horacio Saggion 13:30 - 13:55 Effective Bitext Extraction from Comparable Corpora Using a Combination of Three Different Approaches Steinþór Steingrímsson, Pintu Lohar, Hrafn Loftsson and Andy Way 13:55 - 14:10 Coffee break 14:10 - 14:35 Majority Voting with Bidirectional Pre-translation For Bitext Retrieval Alexander G. Jones and Derry Tanti Wijaya 14:35 - 15:00 Extracting IPA in Wiktionary: Experiments on Multilingual Syllabification and Stress Prediction Winston Wu and David Yarowsky 15:00 - 15:55 Invited presentation Title tba Sujith Ravi 15:55 - 16:00 Closing _______________________________________________ Mt-list site list [email protected] https://lists.eamt.org/cgi-bin/mailman/listinfo/mt-list
