XLM-RoBERTa Base for Igbo (xlm_roberta_base_finetuned_igbo)

Description

xlm_roberta_base_finetuned_igbo is a Igbo RoBERTa model obtained by fine-tuning xlm-roberta-base model on Igbo language texts. It provides better performance than the XLM-RoBERTa on named entity recognition datasets.

Specifically, this model is an xlm-roberta-base model that was fine-tuned on the Igbo corpus.

Predicted Entities

Download

How to use

embeddings = XlmRoBertaEmbeddings.pretrained("xlm_roberta_base_finetuned_igbo", "ig") \
      .setInputCols("sentence", "token") \
      .setOutputCol("embeddings")
val embeddings = XlmRoBertaEmbeddings.pretrained("xlm_roberta_base_finetuned_igbo", "ig")
      .setInputCols("sentence", "token")
      .setOutputCol("embeddings")

Model Information

Model Name: xlm_roberta_base_finetuned_igbo
Compatibility: Spark NLP 3.3.0+
License: Open Source
Edition: Official
Input Labels: [token, sentence]
Output Labels: [embeddings]
Language: ig
Case sensitive: true

Data Source

https://huggingface.co/Davlan/xlm-roberta-base-finetuned-igbo

Benchmarking

## Eval results on Test set (F-score, average over 5 runs)

Dataset| XLM-R F1 | ig_roberta F1
-|-|-
[MasakhaNER](https://github.com/masakhane-io/masakhane-ner) | 84.51 | 87.74