Home > Research > Publications & Outputs > Transformer Models for Offensive Language Ident...

Research

Associated organisational units

Electronic data

  • T1-28

    Final published version, 248 KB, PDF document

View graph of relations

Transformer Models for Offensive Language Identification in Marathi

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Published

Standard

Transformer Models for Offensive Language Identification in Marathi. / Nene, Mayuresh; North, Kai; Ranasinghe, Tharindu et al.
Forum for Information Retrieval Evaluation (working notes). CEUR Workshop Proceedings, 2021. p. 273-282 (CEUR Workshop Proceedings; Vol. 3159).

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Harvard

Nene, M, North, K, Ranasinghe, T & Zampieri, M 2021, Transformer Models for Offensive Language Identification in Marathi. in Forum for Information Retrieval Evaluation (working notes). CEUR Workshop Proceedings, vol. 3159, CEUR Workshop Proceedings, pp. 273-282, 13th Annual Meeting of the Forum for Information Retrieval Evaluation, 13/12/21.

APA

Nene, M., North, K., Ranasinghe, T., & Zampieri, M. (2021). Transformer Models for Offensive Language Identification in Marathi. In Forum for Information Retrieval Evaluation (working notes) (pp. 273-282). (CEUR Workshop Proceedings; Vol. 3159). CEUR Workshop Proceedings.

Vancouver

Nene M, North K, Ranasinghe T, Zampieri M. Transformer Models for Offensive Language Identification in Marathi. In Forum for Information Retrieval Evaluation (working notes). CEUR Workshop Proceedings. 2021. p. 273-282. (CEUR Workshop Proceedings).

Author

Nene, Mayuresh ; North, Kai ; Ranasinghe, Tharindu et al. / Transformer Models for Offensive Language Identification in Marathi. Forum for Information Retrieval Evaluation (working notes). CEUR Workshop Proceedings, 2021. pp. 273-282 (CEUR Workshop Proceedings).

Bibtex

@inproceedings{f12f40b6018b4d93ac5debbf248d33cd,
title = "Transformer Models for Offensive Language Identification in Marathi",
abstract = "This paper describes the WLV-RIT entry to the Hate Speech and Offensive Content Identification in English and Indo-Aryan Languages (HASOC) shared task of 2021. The HASOC 2021 organizers provided participants with annotated datasets containing social media posts of English, Hindi and Marathi. We participated in Marathi Subtask 1A: identifying hateful, offensive and profane content. In our methodology, we take advantage of available data from high resource languages by applying cross-lingual transformer-based models and transfer learning to make predictions to Marathi data. Our system achieved a macro F1 score of 0.91 for the test set and it ranked 1 st place out of 25 systems.",
author = "Mayuresh Nene and Kai North and Tharindu Ranasinghe and Marcos Zampieri",
year = "2021",
month = dec,
day = "17",
language = "English",
series = "CEUR Workshop Proceedings",
publisher = "CEUR Workshop Proceedings",
pages = "273--282",
booktitle = "Forum for Information Retrieval Evaluation (working notes)",
note = "13th Annual Meeting of the Forum for Information Retrieval Evaluation, FIRE ; Conference date: 13-12-2021 Through 17-12-2021",

}

RIS

TY - GEN

T1 - Transformer Models for Offensive Language Identification in Marathi

AU - Nene, Mayuresh

AU - North, Kai

AU - Ranasinghe, Tharindu

AU - Zampieri, Marcos

PY - 2021/12/17

Y1 - 2021/12/17

N2 - This paper describes the WLV-RIT entry to the Hate Speech and Offensive Content Identification in English and Indo-Aryan Languages (HASOC) shared task of 2021. The HASOC 2021 organizers provided participants with annotated datasets containing social media posts of English, Hindi and Marathi. We participated in Marathi Subtask 1A: identifying hateful, offensive and profane content. In our methodology, we take advantage of available data from high resource languages by applying cross-lingual transformer-based models and transfer learning to make predictions to Marathi data. Our system achieved a macro F1 score of 0.91 for the test set and it ranked 1 st place out of 25 systems.

AB - This paper describes the WLV-RIT entry to the Hate Speech and Offensive Content Identification in English and Indo-Aryan Languages (HASOC) shared task of 2021. The HASOC 2021 organizers provided participants with annotated datasets containing social media posts of English, Hindi and Marathi. We participated in Marathi Subtask 1A: identifying hateful, offensive and profane content. In our methodology, we take advantage of available data from high resource languages by applying cross-lingual transformer-based models and transfer learning to make predictions to Marathi data. Our system achieved a macro F1 score of 0.91 for the test set and it ranked 1 st place out of 25 systems.

M3 - Conference contribution/Paper

T3 - CEUR Workshop Proceedings

SP - 273

EP - 282

BT - Forum for Information Retrieval Evaluation (working notes)

PB - CEUR Workshop Proceedings

T2 - 13th Annual Meeting of the Forum for Information Retrieval Evaluation

Y2 - 13 December 2021 through 17 December 2021

ER -