# Extractive QA

A BERT-based fine-tuned Turkish medical QA model specialized in extracting answers from medical texts

A QA model fine-tuned on ModernBERT, excelling on the SQuAD dataset, suitable for extractive QA tasks.

An extractive QA model fine-tuned on the SQuAD2.0 dataset based on flan-t5-large, capable of handling both answerable and unanswerable questions.

An extractive QA model fine-tuned on the SQuAD2.0 dataset based on flan-t5-base, capable of handling question-answer pairs including unanswerable questions.

EurekaQA is an AI Q&A model based on advanced machine learning algorithms, capable of automatically extracting information to answer questions by analyzing text data.

This model is a fine-tuned version of neuralmind/bert-base-portuguese-cased on the FaQuAD dataset, designed for Portuguese extractive question answering tasks.

A Japanese QA model fine-tuned on the JaQuAD dataset, suitable for extractive QA tasks

A QA model fine-tuned on SQuAD2.0 dataset based on distilroberta-base, supporting unanswerable questions

This is a RoBERTa-Base QA model fine-tuned on Chinese corpora, suitable for extractive QA tasks.

This is an extractive QA model trained with AutoNLP, capable of extracting answers from given texts.

This is an extractive question-answering model trained with AutoNLP, capable of extracting answers from given text.

Splinter is a self-supervised pre-trained model specifically designed for few-shot QA tasks, utilizing the Recurring Span Selection (RSS) objective for pre-training.

A multilingual QA model based on bert-base-multilingual-uncased, fine-tuned on the XQuAD dataset

XLM-RoBERTa-based extractive QA model for Vietnamese, ranked first in VLSP MRC 2021 evaluation

Splinter is a few-shot QA model pre-trained via self-supervised learning, utilizing the Recurrent Span Selection (RSS) objective to simulate the span selection process in extractive QA.

Vietnamese QA system based on XLM-RoBERTa, supports English, fine-tuned on datasets like SQuAD

This is a RoBERTa large model optimized for Spanish question answering tasks, trained on a large corpus from the Spanish National Library

Spanish Q&A model, fine-tuned from roberta-base-bne, pre-trained on 570GB of text data from the Spanish National Library

BART-based extractive QA model trained on Squad 2.0 dataset with an F1 score of 87.4