Md Omar Faruqe (Riyad)

Md Omar Faruqe (Riyad)

Software Engineer | Backend Systems, Reliability & AI

Posts by Collection

portfolio

publications

Team_Syrax at BLP-2023 Task 1: Data Augmentation and Ensemble Based Approach for Violence Inciting Text Detection in Bangla

Published in Proceedings of the First Workshop on Bangla Language Processing (BLP-2023), co-located with EMNLP 2023, 2023

Semi-supervised self-training, back-translation, and a transformer ensemble for detecting violence-inciting Bangla text. Ranked 12th in post-evaluation of the BLP-2023 shared task.

Recommended citation: Omar Faruqe Riyad, Trina Chakraborty, and Abhishek Dey. 2023. Team_Syrax at BLP-2023 Task 1: Data Augmentation and Ensemble Based Approach for Violence Inciting Text Detection in Bangla. In Proceedings of the First Workshop on Bangla Language Processing (BLP-2023), pages 247–254, Singapore. Association for Computational Linguistics.
Download Paper

Deja Vu at SemEval 2024 Task 9: A Comparative Study of Advanced Language Models for Commonsense Reasoning

Published in Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), co-located with NAACL 2024, 2024

Compares fine-tuned and prompted language models on the BRAINTEASER lateral-thinking benchmark, with data augmentation to improve robustness on commonsense reasoning.

Recommended citation: Trina Chakraborty, Marufur Rahman, and Omar Riyad. 2024. Deja Vu at SemEval 2024 Task 9: A Comparative Study of Advanced Language Models for Commonsense Reasoning. In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), pages 1239–1244, Mexico City, Mexico. Association for Computational Linguistics.
Download Paper

AdversaryAI at BLP-2025 Task 2: A Think, Refine, and Generate (TriGen) System with LoRA and Self-Refinement for Code Generation

Published in Proceedings of the Second Workshop on Bangla Language Processing (BLP-2025), co-located with IJCNLP-AACL 2025, 2025

A Bangla code generation system combining LoRA fine-tuning of open-source models with Chain-of-Thought prompting and an execution-guided self-refinement loop.

Recommended citation: Omar Faruqe Riyad and Jahedul Alam Junaed. 2025. AdversaryAI at BLP-2025 Task 2: A Think, Refine, and Generate (TriGen) System with LoRA and Self-Refinement for Code Generation. In Proceedings of the Second Workshop on Bangla Language Processing (BLP-2025), pages 629–641, Mumbai, India. Association for Computational Linguistics.
Download Paper

talks

teaching