# Multilingual Transfer Learning

BnTQA-mBart is a low-resource Bengali table question answering model based on the mBART architecture, specifically designed for handling Bengali structured table data question answering tasks.

This is a Hebrew sentence embedding model based on AlephBERT, capable of mapping sentences and paragraphs into a 768-dimensional vector space, suitable for tasks such as semantic search and clustering.

This is a Named Entity Recognition (NER) model fine-tuned on the Russian Wikiann dataset based on the xlm-roberta-large model

An abstract generation model fine-tuned from mT5-small, supporting Chinese text summarization tasks

AfroXLMR-mini is created by adapting the XLM-R-miniLM model through masked language model (MLM) training on 17 African languages, covering major African language families and three high-resource languages (Arabic, French, and English).

A compact variant of XLM-R optimized for 17 African languages, enhanced through vocabulary reduction and multilingual adaptive training

A Javanese masked language model based on the BERT architecture, fine-tuned on Javanese Wikipedia data

BARThez is a French sequence-to-sequence pre-trained model based on the BART architecture, particularly suitable for generative tasks such as abstractive summarization.

A Korean Q&A system fine-tuned based on the xlm-roberta-large-squad2 model, demonstrating excellent performance in KorQuAD evaluations.

Multilingual BERT fine-tuned model for Italian hate speech detection, trained using English data