Michael:
This Tuesday I'll be discussing work that tackles the challenges of applying
practical language technologies to endangered/resource-scarce languages.
Since Daniel covered speech technology, I'll be focusing on machine
translation and the many underlying technologies necessary and helpful for
system building. Here are the papers for this week:
Building NLP Systems for Two Resource-Scarce Indigenous Languages:
Mapudungun and Quechua
Christian Monson, Ariadna Font Llitjós, Roberto Aranovich, Lori Levin, Ralf
Brown, Erik Peterson, Jaime Carbonell, and Alon Lavie
http://www.cslu.ogi.edu/~monsonc/Documents-like-pdfs-etc/Papers/LREC-06/Monson.et.al-BuildingNLPSystemsForTwoResourceScarceIndigenousLanguagesMapudungunAndQuechua-LREC-06.pdf
Low Density Language Bootstrapping: The Case of Tajiki Persian
Karine Megerdoomian and Dan Parvaz
http://www.lrec-conf.org/proceedings/lrec2008/pdf/827_paper.pdf
Using Technology Transfer to Advance Automatic Lemmatisation for Setswana
Hendrik J. Groenewald
http://www.aclweb.org/anthology/W/W09/W09-0705.pdf
Proactive Learning for Building Machine Translation Systems for Minority
Languages
Vamshi Ambati and Jaime Carbonell
http://www.aclweb.org/anthology/W/W09/W09-1908.pdf