---
language:
- en
license: apache-2.0
tags:
- t5-large
- text2text-generation
- conversational question rewriting
datasets:
- CANARD
metrics:
- BLEU

model-index:
- name: t5-large-coqr-canard
  results:
  - task:
      type: text2text-generation
      name: conversational question rewriting
    dataset:
      type: CANARD
      name: CANARD
      split: test
    metrics:
      - type: BLEU
        value: 77.8
        name: BLEU

widget:
- text: "Rewrite the question according to the given context to make the dialog fluent using anaphora and ellipsis.\n\nquestion: What else happened during 1977-1981 other than Superstar Billy Graham's return?\n\ncontext: Superstar Billy Graham\nReturn to WWWF (1977-1981)\nWhy did he return to the WWWF?\nan agreement with promoter Vincent J. McMahon (Senior\nWhat was his agreement with McMahon?\nI don't know.\nHow did people respond to his return?\nI don't know."
- text: "Rewrite the question according to the given context to make the dialog fluent using anaphora and ellipsis.\n\nquestion: why did Billy Graham personally sued Zahorian and the WWF?\n\ncontext: Superstar Billy Graham\nDisputes with the McMahons\nwhat disputes did he have?\nGraham personally sued Zahorian and the WWF,"

inference:
  parameters:
    max_length: 100

---

# t5-large-coqr-canard

This model is a fine-tuned version of [t5-large](https://huggingface.co/t5-large) on the [CANARD](https://sites.google.com/view/qanta/projects/canard) dataset.
It achieves the following results on the test set:
- Loss: 0.3064
- Bleu: 77.1979
- Generation Length: 9.576

## Model description

CANARD dataset rewrites the original questions in conversations to make them context-independent (understandable w/o context).
On the contrary, this model is trained to rewrite context-independent questions to conversational questions, aiming to create fluent dialog with anaphora and ellipsis.

Input: 
```
Rewrite the question according to the given context to make the dialog fluent using anaphora and ellipsis.

question: How did people respond to Superstar Billy Graham's return?

context: Superstar Billy Graham
Return to WWWF (1977-1981)
Why did he return to the WWWF?
an agreement with promoter Vincent J. McMahon (Senior
What was his agreement with McMahon?
I don't know.
```

Target:
```
How did people respond to his return?
```

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.001
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 512
- total_eval_batch_size: 512
- optimizer: Adafactor
- lr_scheduler_type: linear
- num_epochs: 1.0

### Training results

| Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
| No log        | 1.0   | 62   | 0.2987          | 77.2361 | 9.4534  |


### Framework versions

- Transformers 4.20.1
- Pytorch 1.11.0+cu113
- Datasets 2.6.1
- Tokenizers 0.12.1