Multilingual Offensive Language Identification with Cross-lingual Embeddings

被引:0
|
作者
Ranasinghe, Tharindu [1 ]
Zampieri, Marcos [2 ]
机构
[1] Univ Wolverhampton, Wolverhampton, England
[2] Rochester Inst Technol, Rochester, NY USA
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Offensive content is pervasive in social media and a reason for concern to companies and government organizations. Several studies have been recently published investigating methods to detect the various forms of such content (e.g. hate speech, cyberbulling, and cyberaggression). The clear majority of these studies deal with English partially because most annotated datasets available contain English data. In this paper, we take advantage of English data available by applying cross-lingual contextual word embeddings and transfer learning to make predictions in languages with less resources. We project predictions on comparable data in Bengali, Hindi, and Spanish and we report results of 0.8415 F1 macro for Bengali, 0.8568 F1 macro for Hindi, and 0.7513 F1 macro for Spanish. Finally, we show that our approach compares favorably to the best systems submitted to recent shared tasks on these three languages, confirming the robustness of cross-lingual contextual embeddings and transfer learning for this task.
引用
收藏
页码:5838 / 5844
页数:7
相关论文
共 50 条
  • [1] Gender Bias in Multilingual Embeddings and Cross-Lingual Transfer
    Zhao, Jieyu
    Mukherjee, Subhabrata
    Hosseini, Saghar
    Chang, Kai-Wei
    Awadallah, Ahmed Hassan
    58TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2020), 2020, : 2896 - 2907
  • [2] Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignment
    Chen, Muhao
    Tian, Yingtao
    Yang, Mohan
    Zaniolo, Carlo
    PROCEEDINGS OF THE TWENTY-SIXTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2017, : 1511 - 1517
  • [3] Investigating cross-lingual training for offensive language detection
    Pelicon, Andraz
    Shekhar, Ravi
    Skrlj, Blaz
    Purver, Matthew
    Pollak, Senja
    PEERJ COMPUTER SCIENCE, 2021, 7 : 2 - 39
  • [4] Cross-Lingual Classification of Political Texts Using Multilingual Sentence Embeddings
    Licht, Hauke
    POLITICAL ANALYSIS, 2023, 31 (03) : 366 - 379
  • [5] Cross-Lingual Word Embeddings
    Søgaard A.
    Vulić I.
    Ruder S.
    Faruqui M.
    Synthesis Lectures on Human Language Technologies, 2019, 12 (02): : 1 - 132
  • [6] Cross-lingual and Multilingual CLIP
    Carlsson, Fredrik
    Eisen, Philipp
    Rekathati, Faton
    Sahlgren, Magnus
    LREC 2022: THIRTEEN INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION, 2022, : 6848 - 6854
  • [7] Cross-Lingual Word Embeddings
    Corro, Caio Filippo
    TRAITEMENT AUTOMATIQUE DES LANGUES, 2019, 60 (01): : 46 - 48
  • [8] Cross-Lingual Word Embeddings
    Agirre, Eneko
    COMPUTATIONAL LINGUISTICS, 2020, 46 (01) : 245 - 248
  • [9] Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models
    Qi, Jirui
    Fernandez, Raquel
    Bisazza, Arianna
    2023 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2023), 2023, : 10650 - 10666
  • [10] Cross-Lingual Ability of Multilingual Masked Language Models: A Study of Language Structure
    Chai, Yuan
    Liang, Yaobo
    Duan, Nan
    PROCEEDINGS OF THE 60TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022), VOL 1: (LONG PAPERS), 2022, : 4702 - 4712