spMMMP at GermEval 2018 Shared Task: Classification of Offensive Content in Tweets using Convolutional Neural Networks and Gated Recurrent Units
Fiche du document
2 octobre 2018
- handle: 10670/1.0g8x3v
- GOid: 0xc1aa5576_0x003a10f8
info:eu-repo/semantics/openAccess
Mots-clés
Linguistics and LiteratureSujets proches
Language (New words, slang, etc.) Units Measurement, Units of Papers World literature Western literature (Western countries) Belles-lettres Linguistic science Science of language Prediction Forecasts Futurology Knowledge, Classification ofCiter ce document
Dirk von Grünigen et al., « spMMMP at GermEval 2018 Shared Task: Classification of Offensive Content in Tweets using Convolutional Neural Networks and Gated Recurrent Units », Elektronisches Publikationsportal der Österreichischen Akademie der Wissenschafte, ID : 10670/1.0g8x3v
Métriques
Partage / Export
Résumé
In this paper, we propose two different systems for classifying offensive language in micro-blog messages from Twitter (”tweet”). The first system uses an ensemble of convolutional neural networks (CNN), whose outputs are then fed to a meta-classifier for the final prediction. The second system uses a combination of a CNN and a gated recurrent unit (GRU) together with a transfer-learning approach based on pretraining with a large, automatically translated dataset.