CAMRL_2017 Computational Approaches to Morphologically Rich Languages

5th July 2017
Liberty Building SR (G.32)
University of Leeds

Workshop Program

 08:30 – 09:00 Registration and Welcome   Sophiko Daraselia, Workshop Orginiser
 Plenary Talks
 09:00 – 10:00   Lemmatisation in Georgian – Problems and  Solutions  Prof Jost Gippert, Institute of Empirical  Linguistics, Goethe University of Frankfurt
 10:00 – 11:00 Morphosyntactic Annotation Schemata  Dr Andrew Hardie, Director of ESRC Centre for  Corpus Approaches to Social Science (CASS),  Lancaster University
 11:00 – 11:20  Coffee and Tea
 11:20 – 11:50  Rule-based Re-annotation Framework for  Georgian  Dialect Corpus  Prof Marina Beridze, Ivane Javakhishvili  Tbilisi State University
 Dr Sophiko Daraselia, School of Languages,  Cultures and Societies, University of Leeds
 11:50 – 12:20  Neural-Network v Linguistics-Informed  Computational Approaches to Morphologically  Rich Languages: a Call to Arms  Dr Eric Atwell, School of Computing,  University of Leeds
 12:20 – 13:20  Lunch
 13:20 – 14:20  Training Event
 Using Structured POS Tagsets in CWB/CQP    Corpus Queries
 Dr Andrew Hardie, Director of ESRC Centre for  Corpus  Approaches to Social Science (CASS),  Lancaster University
 14:20 – 15:20  Poster Session
 15:20 – 15:40  Coffee and Tea
 15:40 – 16:10  Comparing Taggers for Phrase Break Annotation  in the Arabic Quran  Dr Claire Brierley, School of Computing,  University of Leeds
 16:10 – 16:40   Unsupervised Induction of Morphological Lexicon   for Ukrainian  Dr Bogdan Babych, Centre for Translation Studies, University of Leeds
 16:40 – 17:10  Word Embeddings as Features for Supervised    Morphological Analysis in Russian  Anna Pereverzeva, Moscow National Research University
 17:10 – 17:20   Close


The Workshop will be followed by a wine reception and dinner. The Venue TBC.

Poster Session

  • Dr Rusudan Gersamia, Ilia State University and Dr Manana Topadze Gäumann, University of Bern: ‘Problems of the Segmentation and Morphological Annotation of Verbal Prefixes in Megrelian’
  • Dmitri Sitchinava, Vinogradov Russian Language Institute: ‘Word-by-word tagging in multilingual corpus annotation’.
  • Abdulrahman Alosaimy, University of Leeds: ‘Ensemble Joint Segmentation and POS Tagger for Arabic’
  • Luluh Aldhubayi, University of Leeds: ‘Antonymy Relation Extraction from English and Arabic Corpora’
  • Ayman Alghamdi, University of Leeds: ‘Toward a Comprehensive Computational Representations of Arabic Multiword Expressions