NITK-IT_NLP@TamilNLP-ACL2022: Transformer based model for Toxic Span Identification in Tamil

no code implementations • DravidianLangTech (ACL) 2022 • Hariharan LekshmiAmmal, Manikandan Ravikiran, Anand Kumar Madasamy

Toxic span identification in Tamil is a shared task that focuses on identifying harmful content, contributing to offensiveness.

Findings of the Shared Task on Offensive Span Identification fromCode-Mixed Tamil-English Comments

no code implementations • DravidianLangTech (ACL) 2022 • Manikandan Ravikiran, Bharathi Raja Chakravarthi, Anand Kumar Madasamy, Sangeetha S, Ratnavel Rajalakshmi, Sajeetha Thavareesan, Rahul Ponnusamy, Shankar Mahadevan

Offensive content moderation is vital in social media platforms to support healthy online discussions.

Overview of the Shared Task on Machine Translation in Dravidian Languages

no code implementations • DravidianLangTech (ACL) 2022 • Anand Kumar Madasamy, Asha Hegde, Shubhanker Banerjee, Bharathi Raja Chakravarthi, Ruba Priyadharshini, Hosahalli Shashirekha, John McCrae

This paper presents an outline of the shared task on translation of under-resourced Dravidian languages at DravidianLangTech-2022 workshop to be held jointly with ACL 2022.

Machine Translation Translation

Findings of the Shared Task on Offensive Span Identification from Code-Mixed Tamil-English Comments

no code implementations • 12 May 2022 • Manikandan Ravikiran, Bharathi Raja Chakravarthi, Anand Kumar Madasamy, Sangeetha Sivanesan, Ratnavel Rajalakshmi, Sajeetha Thavareesan, Rahul Ponnusamy, Shankar Mahadevan. /

Offensive content moderation is vital in social media platforms to support healthy online discussions.

Overlapping Word Removal is All You Need: Revisiting Data Imbalance in Hope Speech Detection

no code implementations • 12 Apr 2022 • Hariharan RamakrishnaIyer LekshmiAmmal, Manikandan Ravikiran, Gayathri Nisha, Navyasree Balamuralidhar, Adithya Madhusoodanan, Anand Kumar Madasamy, Bharathi Raja Chakravarthi

Our work revisits this issue in hope-speech detection by introducing focal loss, data augmentation, and pre-processing strategies.

Data Augmentation Hope Speech Detection

Developing Successful Shared Tasks on Offensive Language Identification for Dravidian Languages

no code implementations • 5 Nov 2021 • Bharathi Raja Chakravarthi, Dhivya Chinnappa, Ruba Priyadharshini, Anand Kumar Madasamy, Sangeetha Sivanesan, Subalalitha Chinnaudayar Navaneethakrishnan, Sajeetha Thavareesan, Dhanalakshmi Vadivel, Rahul Ponnusamy, Prasanna Kumar Kumaresan

With the fast growth of mobile computing and Web technologies, offensive language has become more prevalent on social networking platforms.

Language Identification