|
--- |
|
datasets: |
|
- squad |
|
tags: |
|
- question-generation |
|
widget: |
|
- text: "Harry Potter is a series of seven fantasy novels written by British author, [HL]J. K. Rowling[HL]." |
|
--- |
|
|
|
# Transformer QG on SQuAD |
|
HLQG is Proposed by [Ying-Hong Chan & Yao-Chung Fan. (2019). A Re-current BERT-based Model for Question Generation.](https://www.aclweb.org/anthology/D19-5821/) |
|
|
|
**This is a Reproduce Version** |
|
|
|
More detail: [p208p2002/Transformer-QG-on-SQuAD](https://github.com/p208p2002/Transformer-QG-on-SQuAD) |
|
|
|
## Usage |
|
### Input Format |
|
``` |
|
C' = [c1, c2, ..., [HL], a1, ..., a|A|, [HL], ..., c|C|] |
|
``` |
|
### Input Example |
|
``` |
|
Harry Potter is a series of seven fantasy novels written by British author, [HL]J. K. Rowling[HL]. |
|
``` |
|
> # Who wrote Harry Potter? |
|
|
|
## Data setting |
|
We report two dataset setting as Follow |
|
|
|
### SQuAD |
|
- train: 87599\\t |
|
- validation: 10570 |
|
> [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://arxiv.org/abs/1606.05250) |
|
|
|
### SQuAD NQG |
|
- train: 75722 |
|
- dev: 10570 |
|
- test: 11877 |
|
> [Learning to Ask: Neural Question Generation for Reading Comprehension](https://arxiv.org/abs/1705.00106) |
|
|
|
## Available models |
|
- BART |
|
- GPT2 |
|
- T5 |
|
|
|
## Expriments |
|
We report score with `NQG Scorer` which is using in SQuAD NQG. |
|
|
|
If not special explanation, the size of the model defaults to "base". |
|
|
|
### SQuAD |
|
Model |Bleu 1|Bleu 2|Bleu 3|Bleu 4|METEOR|ROUGE-L| |
|
---------------------------------|------|------|------|------|------|-------| |
|
BART-HLSQG |54.67 |39.26 |30.34 |24.15 |25.43 |52.64 | |
|
GPT2-HLSQG |49.31 |33.95 |25.41| 19.69 |22.29 |48.82 | |
|
T5-HLSQG |54.29 |39.22 |30.43 |24.26 |25.56 |53.11 | |
|
|
|
### SQuAD NQG |
|
Model |Bleu 1|Bleu 2|Bleu 3|Bleu 4|METEOR|ROUGE-L| |
|
---------------------------------|------|------|------|------|------|-------| |
|
BERT-HLSQG (Chan et al.) |49.73 |34.60 |26.13 |20.33 |23.88 |48.23 | |
|
BART-HLSQG |54.12 |38.19 |28.84 |22.35 |24.55 |51.03 | |
|
GPT2-HLSQG |49.82 |33.69 |24.71 |18.63 |21.90 |47.60 | |
|
T5-HLSQG |53.13 |37.60 |28.62 |22.38 |24.48 |51.20 | |
