Programme: Workshop on Standards for Text Annotation in African languages

Workshop on Standards for Text Annotation in African languages

SABS, 1 Dr Lategan Avenue, Groenkloof, Pretoria

18 September 2006

StanSA TC 37: TERMINOLOGY, OTHER LANGUAGE AND CONTENT RESOURCES

PROGRAMME

09:00-10:00              Registration (please arrive at 09:30 at the latest, since there is a security procedure at the entrance which takes time)

Tea/Coffee

10:00 – 10:30           ISO Standards for language processing

Justus Roux (Stellenbosch University Centre for Language and Speech Technology)

10:30 – 10:40           Discussion

10:40 – 11:10           Choices in POS-tagging of Northern Sotho texts: comments on early experience

Ulrich Heid; Gertrud Faasz (IMS, University of Stuttgart), Elsabe Taljard (Department of African Languages, University of Pretoria)

11:10 – 11:20           Discussion

11:20 – 11:50           A word-class tagset for Setswana

                                   Rigardt Pretorius (North West University)

11:50 – 12:00           Discussion

12:00 – 12:30           Tagging an agglutinating language

Rusandre Hendrikse (Department of Linguistics, University of South Africa)

12:30 – 12:40           Discussion

12:40 – 13:40           Lunch

13:40 – 16:00           Discussion towards the proposed outcomes of this workshop:

(a)   consensus on the procedure to be followed on standardisation of the structure of a tagging scheme

(b)   proposals for standardised tagsets for the African languages

(c)   fostering cooperation between role players in the field in South Africa

No registration fee, but lunch is for your own account.

Closing date for workshop registration:

14 September 2006.

Please register with:

Prof. Sonja Bosch

boschse@unisa.ac.za

Convenor: ALASA SIG