Hailay/VEXMLM-Amharic-NER

VEXMLM — Amharic NER

Amharic token classification fine-tuned from `Hailay/VEXMLM`, the vocabulary-extended XLM-R for Ge'ez-script languages.

Official implementation: https://github.com/hailaykidu/VEXMLM

Labels cover PER, ORG, LOC and DATE in BIO format (9 classes).

Five-seed benchmark evaluation

Fine-tuned independently under seeds 42–46 with one configuration (hash ce27cc194946) on an A100-PCIE-40GB. Reported as mean ± standard deviation over the five runs, on the dataset's test split.

These are the paper's verified results. They come from the five-seed evaluation described above — not from interactive use.

Interactive inference vs. benchmark

Benchmark evaluation is the five-seed measurement on the held-out test split, shown in the table above.

Interactive inference is what the usage example below performs: Enter arbitrary Amharic text and inspect the predicted entity spans. Predictions on arbitrary user input are demonstrations only and do not produce or reproduce the benchmark score.

Repository layout

Five independently fine-tuned checkpoints, one per seed. The reported benchmark score is the mean ± standard deviation over all five; no single seed is the "five-seed model."

seed-42/  seed-43/  seed-44/  seed-45/  seed-46/

Load a specific seed with the subfolder argument, as in the example below.

Fine-tuning

Fine-tuned from `Hailay/VEXMLM`, a vocabulary-extended XLM-R (280,002 subwords, 30,000 Ge'ez tokens merged into the SentencePiece model) after continued MLM pretraining.

Runs are bit-reproducible: enable_full_determinism, CUBLAS_WORKSPACE_CONFIG=:4096:8, dataloader_num_workers=0.

Usage

from transformers import AutoTokenizer, AutoModelForTokenClassification
import torch

repo = "Hailay/VEXMLM-Amharic-NER"
tokenizer = AutoTokenizer.from_pretrained(repo, subfolder="seed-42")
model = AutoModelForTokenClassification.from_pretrained(repo, subfolder="seed-42")
model.eval()

words = "ኢትዮጵያ በአፍሪካ ቀንድ የምትገኝ ሀገር ናት።".split()
enc = tokenizer(words, is_split_into_words=True, return_tensors="pt", truncation=True)

with torch.no_grad():
    pred = model(**enc).logits.argmax(-1)[0].tolist()

seen = set()
for p, w in zip(pred, enc.word_ids(0)):
    if w is None or w in seen:
        continue
    seen.add(w)
    print(words[w], "->", model.config.id2label[p])

Limitations

• —Fine-tuned for Amharic on MasakhaNER (Amharic) only; performance on other languages, domains or label schemes is not characterised.
• —The base model covers Amharic and Tigrinya; other Ge'ez-script languages were not part of pretraining.
• —Corpora are drawn largely from religious and news domains, and the model may reflect those distributions and any biases in them.
• —Single-configuration study: no hyperparameter search was performed, and baseline comparisons in the paper are single-seed.

Reproducibility

The fine-tuning launcher, evaluation code and per-run result records are in the official repository: https://github.com/hailaykidu/VEXMLM

sbatch scripts/slurm_stage2_spm_seeds.sh    # 6 tasks × 5 seeds
python3 evaluation/export_spm_results.py    # regenerates the metrics table

Citation

@inproceedings{teklehaymanot2026vexmlm,
  title     = {Expanding the Lexicon of Ge'ez Based African Languages:
               A Comparative Study of Amharic and Tigrinya},
  author    = {Teklehaymanot, Hailay Kidu and Yadeta, Gebregziabihier and
               Nejdl, Wolfgang},
  booktitle = {Proceedings of the Workshop on Language Models for
               Underserved Communities (LM4UC) at IJCAI},
  year      = {2026}
}

Accepted at the LM4UC Workshop, IJCAI 2026.

License

Apache 2.0, following xlm-roberta-base.