language: en
datasets:
- squad_v2
T5-small fine-tuned on SQuAD v2
Google's T5 (small) fine-tuned on SQuAD v2 for Q&A downstream task.
Details of T5
The T5 model was presented in Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer by Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J. Liu in Here the abstract:
Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP). The effectiveness of transfer learning has given rise to a diversity of approaches, methodology, and practice. In this paper, we explore the landscape of transfer learning techniques for NLP by introducing a unified framework that converts every language problem into a text-to-text format. Our systematic study compares pre-training objectives, architectures, unlabeled datasets, transfer approaches, and other factors on dozens of language understanding tasks. By combining the insights from our exploration with scale and our new “Colossal Clean Crawled Corpus”, we achieve state-of-the-art results on many benchmarks covering summarization, question answering, text classification, and more. To facilitate future work on transfer learning for NLP, we release our dataset, pre-trained models, and code.
Details of the downstream task (Q&A) - Dataset 📚 🧐 ❓
Dataset ID: squad_v2 from Huggingface/NLP
| Dataset | Split | # samples |
|---|---|---|
| squad_v2 | train | 130319 |
| squad_v2 | valid | 11873 |
How to load it from nlp
train_dataset = nlp.load_dataset('squad_v2', split=nlp.Split.TRAIN)
valid_dataset = nlp.load_dataset('squad_v2', split=nlp.Split.VALIDATION)
Check out more about this dataset and others in NLP Viewer
Model fine-tuning 🏋️
The training script is a slightly modified version of this awesome one by Suraj Patil
Results 📝
| Metric | # Value |
|---|---|
| EM | 69.46 |
| F1 | 73.01 |
Model in Action 🚀
from transformers import AutoModelWithLMHead, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("mrm8488/t5-small-finetuned-squadv2")
model = AutoModelWithLMHead.from_pretrained("mrm8488/t5-small-finetuned-squadv2")
def get_answer(question, context):
input_text = "question: %s context: %s </s>" % (question, context)
features = tokenizer([input_text], return_tensors='pt')
output = model.generate(input_ids=features['input_ids'],
attention_mask=features['attention_mask'])
return tokenizer.decode(output[0])
context = "Manuel has created RuPERTa-base (a Spanish RoBERTa) with the support of HF-Transformers and Google"
question = "Who has supported Manuel?"
get_answer(question, context)
# output: 'HF-Transformers and Google'
Created by Manuel Romero/@mrm8488 | LinkedIn
Made with ♥ in Spain