Description
A tutorial, organized between Estonia and Sweden, aims to pass on experiences of automatic sentence selection from corpora for Swedish to our partners in Estonia. A representative from Slovenia is joining the tutorial.
Organizers: Ildikó Pilán and Elena Volodina (University of Gothenburg, Språkbanken, Sweden)
Participants: Kristina Koppel (Institute of the Estonian Language / University of Tartu) and Iztok Kosem (Trojina, Institute for Applied Slovene Studies / University of Ljubljana)
Program
Date | Time | Room | Clarin tutorial – program point |
26/5 (Friday) | 9-16 | K234 | XML processing with Python, data preparation (Kristina, Ildikó) |
29/5 (Monday) | 9-12 | C450 | Mini-workshop https://sweclarin.se/swe/mini-workshop-collocations-and-sentence-selection |
14-17 | K234 | Install/introduce tools (numpy, scikit learn, WEKA) | |
30/5 (Tuesday) | 9-11 | L307 | Machine learning (ML): intro [slides] |
11-12 | - | Practical session: ML - WEKA | |
12-15 | - | Supervised individual work | |
15-17 | K234 | Practical session: ML - scikit learn | |
Dinner | |||
31/5 (Wednesday) | 8-12 | K234 | Practical session: features |
13-15
15-17 |
K234 |
Supervised individual work
Individual work |
|
1/6 (Thursday) | 8-13 | L307 | Supervised individual work |
13-17 | K234 | Individual work |