We describe our approach (MB-Courage team) in the Sexism Identification in Social Networks Shared Task (EXIST). We submitted three runs for each task, two of them based on Graph Convolutional Neural Networks (GCN) exploring different edge creation strategies and one combining graph embeddings from different GCN through ensemble methods. In addition, we explored different GCN models and text-to- graph strategies. We identified that in Task 2 the models take advantage of the syntactic relationship between words encoded in the graph, while it did not strongly impact Task 1. Moreover, the models generalized the task while maintaining similar (in some cases better) results in the social network that was not used in training. On average, our best models performed similarly across languages and social media, ranking 37th (out of 72 runs) for Task 1 and 40th (out of 63) for Task 2.

Wilkens, R., Ognibene, D. (2021). Mb-courage @ exist: Gcn classification for sexism identification in social networks?. In CEUR Workshop Proceedings (pp.420-430). CEUR-WS.

Mb-courage @ exist: Gcn classification for sexism identification in social networks?

Ognibene D.
Ultimo
2021

Abstract

We describe our approach (MB-Courage team) in the Sexism Identification in Social Networks Shared Task (EXIST). We submitted three runs for each task, two of them based on Graph Convolutional Neural Networks (GCN) exploring different edge creation strategies and one combining graph embeddings from different GCN through ensemble methods. In addition, we explored different GCN models and text-to- graph strategies. We identified that in Task 2 the models take advantage of the syntactic relationship between words encoded in the graph, while it did not strongly impact Task 1. Moreover, the models generalized the task while maintaining similar (in some cases better) results in the social network that was not used in training. On average, our best models performed similarly across languages and social media, ranking 37th (out of 72 runs) for Task 1 and 40th (out of 63) for Task 2.
Si
paper
EXIST; Graph Neural Network; MeanPooling; set2set; social media; hate speech; natural language processing;NLP
English
2021 Iberian Languages Evaluation Forum, IberLEF 2021
http://ceur-ws.org/Vol-2943/exist_paper9.pdf
Wilkens, R., Ognibene, D. (2021). Mb-courage @ exist: Gcn classification for sexism identification in social networks?. In CEUR Workshop Proceedings (pp.420-430). CEUR-WS.
Wilkens, R; Ognibene, D
File in questo prodotto:
File Dimensione Formato  
exist_paper9.pdf

accesso aperto

Tipologia di allegato: Publisher’s Version (Version of Record, VoR)
Dimensione 884.01 kB
Formato Adobe PDF
884.01 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/362712
Citazioni
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
Social impact