BibTeX

@inProceedings{bouma-2019-exploring-289484,
	title        = {Exploring Combining Training Datasets for the CLIN 2019 Shared Task on Cross-genre Gender Detection in Dutch},
	abstract     = {We present our entries to the Shared Task on Cross-genre Gender Detection in Dutch at CLIN 2019. We start from a simple logistic regression model with commonly used features, and consider two ways of combining training data from different sources.Our in-genre models do reasonably well, but the cross-genre models area lot worse. Post-task experiments show no clear systematic advantage of one way of combining training data sources over the other, but do suggest  accuracy  can  be  gained  from  a  better  way  of  setting  model hyperparameters.},
	booktitle    = {CEUR Workshop Proceedings, vol 2453. Proceedings of the Shared Task on Cross-Genre Gender Prediction in Dutch at CLIN29 (GxG-CLIN29) co-located with the 29th Conference on Computational Linguistics in The Netherlands (CLIN29). Groningen, The Netherlands, January 31, 2019. Edited by Hessel Haagsma, Tim Kreutz, Masha Medvedeva, Walter Daelemans and Malvina Nissim},
	author       = {Bouma, Gerlof},
	year         = {2019},
	publisher    = {CEUR-WS.org},
	address      = {Aachen },
}