%0 Conference Proceedings
%A Zariquiey, Roberto
%A Alvarado, Claudia
%A Echevarria, Ximena
%A Gomez, Luisa
%A Gonzales, Rosa
%A Illescas, Mariana
%A Oporto, Sabina
%A Blum, Frederic
%A Oncevay, Arturo
%A Vera, Javier
%+ Department of Linguistic and Cultural Evolution, Max Planck Institute for Evolutionary Anthropology, Max Planck Society
%T Building an endangered language resource in the classroom: Universal dependencies for Kakataibo : 
%G eng
%U https://hdl.handle.net/21.11116/0000-000A-A2BF-8
%D 2022
%B LREC 2022
%Z date of event: 2022-06-20 - 2022-06-25
%C Marseille
%X In this paper, we launch a new Universal Dependencies <br>treebank for an endangered language from Amazonia: Kakataibo, a Panoan <br>language spoken in Peru. We first discuss the collaborative methodology <br>implemented, which proved effective to create a treebank in the context <br>of a Computational Linguistic course for undergraduates. Then, we <br>describe the general details of the treebank and the language-specific <br>considerations implemented for the proposed annotation. We finally <br>conduct some experiments on part-of-speech tagging and syntactic <br>dependency parsing. We focus on monolingual and transfer learning <br>settings, where we study the impact of a Shipibo-Konibo treebank, <br>another Panoan language resource
%B Proceedings of the 13th Conference on Language Resources and Evaluation (LREC 2022)
%P 3840 - 3851
%I European Language Resources Association