This repository contains the system description and the codes that we implemented for participating in EACL-2024 Shared Task-5.
-
Updated
Apr 6, 2024 - Jupyter Notebook
This repository contains the system description and the codes that we implemented for participating in EACL-2024 Shared Task-5.
DravidaKavacham is an open-source tool for detecting abusive content in Dravidian (Tamil and Malayalam), focused on harmful language targeting women. Developed as part of the DravidianLangTech@NAACL 2025 shared task, it uses NLP and machine learning for accurate text classification and content analysis.
Morphological analyser for Malayalam — lemma, stem, root, POS, and inflection tags. ~30k words/sec.
Advanced Telugu sentiment analysis for YouTube comments using Meta Llama 3.2 with 4-bit quantization. Features interactive dashboard, code-mixed text support, real-time processing, and comprehensive evaluation metrics. Perfect for analyzing Telugu social media content and movie reviews.
GPT-2 Architecture, Dravidian Models- Tamil, Telugu, Kannada, Malayalam
EACL 2021 paper (SJ_AJ@DravidianLangTech-EACL2021: Task-Adaptive Pre-Training of Multilingual BERT models for Offensive Language Identification)
Brahui dictionary and Urdu-script speech bridge — 254 sourced entries from the Linguistic Survey of India IV (1906) and Bray 1909, in a single HTML file
To associate your repository with the dravidian-languages topic, visit your repo's landing page and select "manage topics."