Edinburgh

Programme

Sunday, July 31, 2011

09:00-09:10   Opening
09:10-10:10 Invited talk by Burr Settles: Combining Learning Strategies to Make the Most of Language Resources
10:10-10:30 Discussion
10:30-11:00 coffee break
11:00-11:30 Dialect Translation: Integrating Bayesian Co-segmentation Models with Pivot based SMT
Michael Paul, Andrew Finch, Paul R. Dixon and Eiichiro Sumita
11:30-12:00 Dialectal to Standard Arabic Paraphrasing to Improve Arabic-English Statistical Machine Translation
Wael Salloum and Nizar Habash
12:00-12:30 PaddyWaC: A Minimally-Supervised Web-Corpus of Hiberno-English
Brian Murphy and Egon W. Stemle
12:30-14:00 lunch break
14:00-14:10 Poster flash
14:10-14:40 Poster session
14:40-15:10 Syntactic transformations for Swiss German dialects
Yves Scherrer
15:10-15:40 Learning word-level dialectal variation as phonological replacement rules using a limited parallel corpus
Mans Hulden, Iñaki Alegria, Izaskun Etxeberria and Montse Maritxalar
15:40-16:10 coffee break
16:10-16:40 Modeling of Stylistic Variation in Social Media with Stretchy Patterns
Philip Gianfortoni, David Adamson and Carolyn P. Rosé
16:40-17:00 Final discussion


Poster presentations:
  • Adapting Slovak ASR for native Germans speaking Slovak
    Štefan Beňuš, Miloš Cerňak, Sakhia Darjaa, Milan Rusko and Marián Trnka
  • WordNet.PTglobal - Extending WordNet.PT to Portuguese varieties
    Palmira Marrafa, Raquel Amaro and Sara Mendes
  • Phone set selection for HMM-based dialect speech synthesis
    Michael Pucher, Nadja Kerschhofer-Puhalo and Dietmar Schabus