This paper describes the Shared Task on Scene Segmentation STSS@KONVENS 2021: The goal is to provide a model that can accurately segment literary narrative texts into scenes and non-scenes. To this end, participants were provided with a set of 20 contemporary dime novels annotated with scene information as training data. The evaluation of the task is split into two tracks: The test set for Track 1 consists of 4 in-domain texts (dime novels), while Track 2 tests the generalisation capabilities of the model on 2 out-of-domain texts (highbrow literature from the 19th century). 5 teams participated in the task and submitted a model for final evaluation as well as a system description paper, with the best-performing models reaching F1-scores of 37 % for Track 1 and 26 % for Track 2. The results show that the task of scene segmentation is very challenging, but also suggest that it is feasible in principle. Detailed evaluation of the predictions reveals that the best-performing model is able to pick up many signals for scene changes, but struggles with the level of granularity that actually constitutes a scene change.
@inproceedings{ Zehe2021ab,
Title = {{Shared Task on Scene Segmentation@KONVENS 2021}},
Author = { Albin Zehe and Leonard Konle and Svenja Guhr and Lea Dümpelmann and Evelyn Gius and Andreas Hotho and Fotis Jannidis and Lucas Kaufmann and Markus Krug and Frank Puppe and Nils Reiter and Annekea Schreiber },
Booktitle = {{Proceedings of the Shared Task on Scene Segmentation}},
Month = { September },
Year = { 2021 }
}
TY -
TI - Shared Task on Scene Segmentation@KONVENS 2021
AU - Albin Zehe
AU - Leonard Konle
AU - Svenja Guhr
AU - Lea Dümpelmann
AU - Evelyn Gius
AU - Andreas Hotho
AU - Fotis Jannidis
AU - Lucas Kaufmann
AU - Markus Krug
AU - Frank Puppe
AU - Nils Reiter
AU - Annekea Schreiber
PY - 2021
J2 - Proceedings of the Shared Task on Scene Segmentation
ER -