Proceedings of the GermEval 2018 Workshop 14th Conference on Natural Language Processing - KONVENS 2018
|
Verlag der Österreichischen Akademie der Wissenschaften Austrian Academy of Sciences Press
A-1011 Wien, Dr. Ignaz Seipel-Platz 2
Tel. +43-1-515 81/DW 3420, Fax +43-1-515 81/DW 3400 https://verlag.oeaw.ac.at, e-mail: verlag@oeaw.ac.at |
|
DATUM, UNTERSCHRIFT / DATE, SIGNATURE
BANK AUSTRIA CREDITANSTALT, WIEN (IBAN AT04 1100 0006 2280 0100, BIC BKAUATWW), DEUTSCHE BANK MÜNCHEN (IBAN DE16 7007 0024 0238 8270 00, BIC DEUTDEDBMUC)
|
Proceedings of the GermEval 2018 Workshop 14th Conference on Natural Language Processing - KONVENS 2018
Gregor Wiedemann,
Eugen Ruppert,
Raghav Jindal,
Chris Biemann
S. 85 - 94 Verlag der Österreichischen Akademie der Wissenschaften
Abstract: We investigate different strategies for automatic offensive language classification on German Twitter data. For this, we employ a sequentially combined BiLSTMCNN neural network. Based on this model, three transfer learning tasks to improve the classification performance with background knowledge are tested. We compare 1. Supervised category transfer: social media data annotated with near-offensive language categories, 2. Weakly-supervised category transfer: tweets annotated with emojis they contain, 3. Unsupervised category transfer: tweets annotated with topic clusters obtained by Latent Dirichlet Allocation (LDA). Further, we investigate the effect of three different strategies to mitigate negative effects of ‘catastrophic forgetting’ during transfer learning. Our results indicate that transfer learning in general improves offensive language detection. Best results are achieved from pre-training our model on the unsupervised topic clustering of tweets in combination with thematic user cluster information. Published Online: 2018/11/21 07:52:29 Document Date: 2018/10/02 12:00:00 Object Identifier: 0xc1aa5576 0x003a10ec Rights: . Die Konferenz zur Verarbeitung Natürlicher Sprache (KONVENS) soll den
Erfahrungsaustausch auf hohem Niveau durch die Vorstellung
computerlinguistischer Grundlagenforschung und ausgewählte
Praxisvorträge von Experten befördern.
|
Verlag der Österreichischen Akademie der Wissenschaften Austrian Academy of Sciences Press
A-1011 Wien, Dr. Ignaz Seipel-Platz 2
Tel. +43-1-515 81/DW 3420, Fax +43-1-515 81/DW 3400 https://verlag.oeaw.ac.at, e-mail: verlag@oeaw.ac.at |