Thumbnail Image
Item

RGCL at GermEval 2019: offensive language detection with deep learning

Plum, A
; 
Ranasinghe, Tharindu
; ; 
Mitkov, R
Authors
Plum, A
 Ranasinghe, Tharindu
 Orasan, Constantin
 Mitkov, R
Editors
Other contributors
Affiliation
Epub Date
Issue Date
2019-10-08
Submitted date
Subjects
Natural Language Processing
 deep learning
 aggression identification
Show all metadata
Files
Thumbnail Image
Germeval_Task_2_2019_paper_13.pdf
Adobe PDF, 129.28 KB
Alternative
Abstract
This paper describes the system submitted by the RGCL team to GermEval 2019 Shared Task 2: Identification of Offensive Language. We experimented with five different neural network architectures in order to classify Tweets in terms of offensive language. By means of comparative evaluation, we select the best performing for each of the three subtasks. Overall, we demonstrate that using only minimal preprocessing we are able to obtain competitive results.
Citation
Plum, A., Ranasinghe, T., Orasan, C. and Mitkov, R. (2019) RGCL at GermEval 2019: offensive language detection with deep learning. Preliminary proceedings of the 15th Conference on Natural Language Processing (KONVENS 2019). Erlangen, Germany, pp. 421-426.
Publisher
German Society for Computational Linguistics & Language Technology
Journal
Research Unit
URI
http://hdl.handle.net/2436/622866
DOI
PubMed ID
PubMed Central ID
Embedded videos
Additional Links
https://2019.konvens.org/proceedings
Type
Conference contribution
Language
en
Description
Series/Report no.
ISSN
EISSN
ISBN
ISMN
Gov't Doc #
Sponsors
Rights
Research Projects
Organizational Units
Journal Issue
Embedded videos
Collections
Research Institute in Information and Language Processing