Abstrakti
This paper presents the different models submitted by the LT@Helsinki team for the SemEval2020 Shared Task 12. Our team participated in sub-tasks A and C; titled offensive language identification and offense target identification, respectively. In both cases we used the so called Bidirectional Encoder Representation from Transformer (BERT), a model pre-trained by Google and fine-tuned by us on the OLID dataset. The results show that offensive tweet classification is one of several language-based tasks where BERT can achieve state-of-the-art results.
Alkuperäiskieli | Englanti |
---|---|
Otsikko | Proceedings of the 14th International Workshop on Semantic Evaluation |
Kustantaja | International Committee on Computational Linguistics (ICCL |
Sivumäärä | 7 |
ISBN (painettu) | 978-1-952148-31-6 |
Tila | Julkaistu - 2020 |
OKM-julkaisutyyppi | A4 Artikkeli konferenssijulkaisussa |
Tapahtuma | International Workshop on Semantic Evaluation - Barcelona, Espanja Kesto: 12 jouluk. 2020 → 13 jouluk. 2020 http://alt.qcri.org/semeval2020/ |
Workshop
Workshop | International Workshop on Semantic Evaluation |
---|---|
Lyhennettä | SemEval |
Maa/Alue | Espanja |
Kaupunki | Barcelona |
Ajanjakso | 12/12/2020 → 13/12/2020 |
Muu | Collocated with The 28th International Conference on Computational Lingustics (COLING-2020) |
www-osoite |