FlorUniTo@TRAC-2: Retrofitting Word Embeddings on an Abusive Lexicon for Aggressive Language Detection

Anna Koufakou, Valerio Basile, Viviana Patti


Abstract
This paper describes our participation to the TRAC-2 Shared Tasks on Aggression Identification. Our team, FlorUniTo, investigated the applicability of using an abusive lexicon to enhance word embeddings towards improving detection of aggressive language. The embeddings used in our paper are word-aligned pre-trained vectors for English, Hindi, and Bengali, to reflect the languages in the shared task data sets. The embeddings are retrofitted to a multilingual abusive lexicon, HurtLex. We experimented with an LSTM model using the original as well as the transformed embeddings and different language and setting variations. Overall, our systems placed toward the middle of the official rankings based on weighted F1 score. However, the results on the development and test sets show promising improvements across languages, especially on the misogynistic aggression sub-task.
Anthology ID:
2020.trac-1.17
Volume:
Proceedings of the Second Workshop on Trolling, Aggression and Cyberbullying
Month:
May
Year:
2020
Address:
Marseille, France
Venues:
LREC | TRAC | WS
SIG:
Publisher:
European Language Resources Association (ELRA)
Note:
Pages:
106–112
Language:
English
URL:
https://aclanthology.org/2020.trac-1.17
DOI:
Bibkey:
Cite (ACL):
Anna Koufakou, Valerio Basile, and Viviana Patti. 2020. FlorUniTo@TRAC-2: Retrofitting Word Embeddings on an Abusive Lexicon for Aggressive Language Detection. In Proceedings of the Second Workshop on Trolling, Aggression and Cyberbullying, pages 106–112, Marseille, France. European Language Resources Association (ELRA).
Cite (Informal):
FlorUniTo@TRAC-2: Retrofitting Word Embeddings on an Abusive Lexicon for Aggressive Language Detection (Koufakou et al., TRAC 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/2020.trac-1.17.pdf