GEC and word generation for Tamil (IndicGEC / IndicWG shared tasks)
Grammatical error correction for Tamil is much harder than for English — agglutinative morphology, free word order, and limited annotated data all make the problem qualitatively different. We participate in the IndicGEC and IndicWG shared tasks, developing systems for detecting and correcting errors in Tamil text and for word generation in Indian languages.
Team: J Harish Rajeshwaran, S Ashwin Arumugam
References
2025
BHASHA ’25
Findings of the IndicGEC and IndicWG Shared Task at BHASHA 2025
Pramit Bhattacharyya, Karthika N J, Hrishikesh Terdalkar, and 4 more authors
In Proceedings of the 1st Workshop on Benchmarks, Harmonization, Annotation, and Standardization for Human-Centric AI in Indian Languages (BHASHA 2025), Dec 2025
This overview paper presents the findings of the two shared tasks organized as part of the 1st Workshop on Benchmarks, Harmonization, Annotation, and Standardization for Human-Centric AI in Indian Languages (BHASHA) co-located with IJCNLP-AACL 2025. The shared tasks are: (1) Indic Grammar Error Correction (IndicGEC) and (2) Indic Word Grouping (IndicWG). For GEC, participants were tasked with producing grammatically correct sentences based on given input sentences in five Indian languages. For WG, participants were required to generate a word-grouped variant of a provided sentence in Hindi. The evaluation metric used for GEC was GLEU, while Exact Matching was employed for WG. A total of 14 teams participated in the final phase of the Shared Task 1; 2 teams participated in the final phase of Shared Task 2. The maximum GLEU scores obtained for Hindi, Bangla, Telugu, Tamil and Malayalam languages are respectively 85.69, 95.79, 88.17, 91.57 and 96.02 for the IndicGEC shared task. The highest exact matching score obtained for IndicWG shared task is 45.13%.
@inproceedings{bhattacharyya-etal-2025-findings,title={Findings of the {I}ndic{GEC} and {I}ndic{WG} Shared Task at {BHASHA} 2025},author={Bhattacharyya, Pramit and N J, Karthika and Terdalkar, Hrishikesh and Jagadeeshan, Manoj Balaji and Nigam, Shubham Kumar and Susmitha, Arvapalli Sai and Bhattacharya, Arnab},booktitle={Proceedings of the 1st Workshop on Benchmarks, Harmonization, Annotation, and Standardization for Human-Centric AI in Indian Languages (BHASHA 2025)},month=dec,year={2025},address={Mumbai, India},publisher={Association for Computational Linguistics},url={https://aclanthology.org/2025.bhasha-1.12/},pages={127--134},}