🚀 bert-base-multilingual-uncased for multilingual QA
This project utilizes the bert-base-multilingual-uncased model for multilingual extractive question - answering tasks, trained and tested on the XQuAD dataset.
🚀 Quick Start
This model is designed for multilingual extractive question - answering. It is trained and tested on the XQuAD dataset.
✨ Features
- Multilingual Support: Capable of handling multiple languages for question - answering tasks.
- Extractive QA: Specifically designed for extractive question - answering tasks.
📦 Installation
No specific installation steps are provided in the original document.
💻 Usage Examples
Basic Usage
In Transformers
from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
model_name = "alon-albalak/bert-base-multilingual-xquad"
nlp = pipeline('question-answering', model=model_name, tokenizer=model_name)
QA_input = {
'question': 'Why is model conversion important?',
'context': 'The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks.'
}
res = nlp(QA_input)
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
In FARM
from farm.modeling.adaptive_model import AdaptiveModel
from farm.modeling.tokenization import Tokenizer
from farm.infer import QAInferencer
model_name = "alon-albalak/bert-base-multilingual-xquad"
nlp = QAInferencer.load(model_name)
QA_input = [{"questions": ["Why is model conversion important?"],
"text": "The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks."}]
res = nlp.inference_from_dicts(dicts=QA_input, rest_api_schema=True)
model = AdaptiveModel.convert_from_transformers(model_name, device="cpu", task_type="question_answering")
tokenizer = Tokenizer.load(model_name)
In Haystack
reader = FARMReader(model_name_or_path="alon-albalak/bert-base-multilingual-xquad")
reader = TransformersReader(model="alon-albalak/bert-base-multilingual-xquad",tokenizer="alon-albalak/bert-base-multilingual-xquad")
💡 Usage Tip
Usage instructions for FARM and Haystack were adopted from https://huggingface.co/deepset/xlm-roberta-large-squad2
📚 Documentation
Overview
Property |
Details |
Model Type |
bert-base-multilingual-uncased |
Downstream task |
Extractive QA |
Training Data |
XQuAD |
Testing Data |
XQuAD |
Hyperparameters
batch_size = 48
n_epochs = 6
max_seq_len = 384
doc_stride = 128
learning_rate = 3e-5
Performance
Evaluated on held - out test set from XQuAD
"exact_match": 64.6067415730337,
"f1": 79.52043478874286,
"test_samples": 2384