t5-base-finetuned-question-answering

T5 for Generative Question Answering

This model is the result produced by Christian Di Maio and Giacomo Nunziati for the Language Processing Technologies exam. Reference for Google's T5 fine-tuned on DuoRC for Generative Question Answering by just prepending the question to the context.

Code

The code used for T5 training is available at this repository.

Results

The results are evaluated on:

• DuoRC/SelfRC -> Test Subset
• DuoRC/ParaphraseRC -> Test Subset
• SQUADv1 -> Validation Subset

Removing all tokens not related to dictionary words from the evaluation metrics. The model used as reference is BERT finetuned on SQUAD v1.

How to use it 🚀

from  transformers  import  AutoTokenizer, AutoModelWithLMHead, pipeline

model_name = "MaRiOrOsSi/t5-base-finetuned-question-answering"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelWithLMHead.from_pretrained(model_name)
question = "What is 42?"
context = "42 is the answer to life, the universe and everything"
input = f"question: {question} context: {context}"
encoded_input = tokenizer([input],
							 return_tensors='pt',
							 max_length=512,
							 truncation=True)
output = model.generate(input_ids = encoded_input.input_ids,
							attention_mask = encoded_input.attention_mask)
output = tokenizer.decode(output[0], skip_special_tokens=True)
print(output)

Citation

Created by Christian Di Maio and Giacomo Nunziati

Made with <span style="color: #e25555;">♥</span> in Italy