To the top

Page Manager: Webmaster
Last update: 9/11/2012 3:13 PM

Tell a friend about this page
Print version

Exploring Combining Train… - University of Gothenburg, Sweden Till startsida
Sitemap
To content Read more about how we use cookies on gu.se

Exploring Combining Training Datasets for the CLIN 2019 Shared Task on Cross-genre Gender Detection in Dutch

Conference paper
Authors Gerlof Bouma
Published in 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
ISSN 1613-0073
Publisher CEUR-WS.org
Place of publication Aachen
Publication year 2019
Published at Department of Swedish
Language en
Links ceur-ws.org/Vol-2453/paper02.pdf
Subject categories Computational linguistics

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.

Page Manager: Webmaster|Last update: 9/11/2012
Share:

The University of Gothenburg uses cookies to provide you with the best possible user experience. By continuing on this website, you approve of our use of cookies.  What are cookies?