Natural Don't Know Response Model

Fine-tuned on Google's T5 using a combination of a dependency-rule based data and Quora Question Pairs(QQP) dataset for Don't Know Response Generation task.

Additional information about this model:

How to use

from transformers import T5ForConditionalGeneration, T5Tokenizer
model_name = "ashish-shrivastava/dont-know-response"
model = T5ForConditionalGeneration.from_pretrained(model_name)
tokenizer = T5Tokenizer.from_pretrained(model_name)

input = "Where can I find good Italian food ?"
input_ids = tokenizer.encode(input, return_tensors="pt")
outputs = model.generate(input_ids)
decoded_output = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(decoded_output) # I'm not sure where you can get good quality Italian food.


n_epochs = 2
base_LM_model = "T5-base"
max_seq_len = 256
learning_rate = 3e-4
adam_epsilon = 1e-8
train_batch_size = 6

BibTeX entry and citation info

      title={Saying No is An Art: Contextualized Fallback Responses for Unanswerable Dialogue Queries}, 
      author={Ashish Shrivastava and Kaustubh Dhole and Abhinav Bhatt and Sharvani Raghunath},
Downloads last month
Hosted inference API
Text2text Generation