Kannada Named Entity & Morphological Segmentation Benchmark
Objective & Abstract
Developing a standardized tokenization and morphological parsing pipeline for low-resource Kannada administrative documents with comparative subword vocabulary boundary metrics.
Investigated Methodologies
- Subword BPE evaluation
- Morphological segmentation
- Cross-dialect testing
Datasets & Benchmarking Corpora
AIAC Kannada Admin Corpus (Curated)
IndicCorp Kannada
All training and evaluation datasets undergo ethics audit and licensing compliance per AIAC Research Council standards.