Fine-tuned bert-base-multilingual-cased that restores punctuation around Eastern Armenian participle clauses, framed as 4-class token labeling. From the CODASSCA 2026 paper Sequence Labeling for Low-Resource Syntax: Automatic Punctuation of Armenian Participle Clauses.

0 O · 1 COMMA_AFTER · 2 BUTH_AFTER · 3 REMOVE_COMMA

Training: 15% negative under-sampling of the majority O class; lower 6 layers frozen; hyper-parameters tuned with Optuna (21 trials). See artifacts/ for the raw checkpoint, best config, trial log and final results; training/ holds the notebook.

Best results come from a soft-vote of this model with the BiLSTM at alpha=0.45: P = 0.45 * P_bilstm + 0.55 * P_mbert (macro-F1 0.6745 on Shtemaran). See the bilstm-armenian-participle-punct repo.