Tasnim, NaziaShihab, IstiakSushmit, Asif ShahriyarBethard, StevenSadeque, Farig2026-09-062026-09-062022-01-01Tasnim, N., Shihab, Md. I., Shahriyar Sushmit, A., Bethard, S., & Sadeque, F. (2022). TEAM-Atreides at SemEval-2022 Task 11: On leveraging data augmentation and ensemble to recognize complex Named Entities in Bangla. Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), 1524–1530. https://doi.org/10.18653/v1/2022.semeval-1.20997819559178032-s2.0-85137554053https://hdl.handle.net/10361/29775Biological and healthcare domains, artistic works, and organization names can all have nested, overlapping, discontinuous entity mentions that may be syntactically or semantically ambiguous in practice. Traditional sequence tagging algorithms are unable to recognize these complex mentions because they violate the assumptions upon which sequence tagging schemes are founded. In this paper, we describe our contribution to SemEval 2022 Task 11 on identifying such complex named entities. We leveraged an ensemble of ELECTRA-based models exclusively pretrained on the Bangla language with ELECTRA-based monolingual models pretrained on English to achieve competitive performance. Besides providing a system description, we also present the outcomes of our experiments on architectural decisions, dataset augmentations and post-competition findings. © 2022 Association for Computational Linguistics.1524 - 1530en-USArchitectural decisionArtistic worksBiological domainCompetitive performanceData augmentationData ensembleHealthcare domainsNamed entitiesSystem descriptionBengali language--Data processing.Natural language processing (Computer science).Conference Paper10.18653/v1/2022.semeval-1.209