---
language:
 - zh

tags:
 - Question Answering
 - Machine Reading
 - Text Generation
 - Pretrained Chinese T5-Large model

metrics:
 - RougeL
 - BLEU-4
 - F1
 - EM
 - Contain Answer Rate

licence: apache-2.0
---
# T5 for Chinese Question Answering
Randeng-T5-784M-QA-Chinese


## Brief Introduction
This T5-Large model, is the first pretrained generative question answering model for Chinese in huggingface. It was pretrained on the Wudao 180G corpus, and finetuned on Chinese SQuAD and CMRC2018 dataset. It can produce a fluent and accurate answer given a passage and question.

这是huggingface上首个中文的生成式问答模型。它基于T5-Large结构，使用悟道180G语料进行预训练，在翻译的中文SQuAD和CMRC2018两个阅读理解数据集上进行微调。输入一篇文章和一个问题，可以生成准确流畅的回答。

## Performance
  
 CMRC 2018 dev (Original span prediction task, we cast it as a generative QA task)

 CMRC 2018的测试集上的效果（原始任务是一个起始和结束预测问题，这里作为一个生成回答的问题）
  
   | model | F1 | EM | Contain Answer Rate| RougeL | BLEU-4 |
   |-------|----|----|--------------------|--------|--------|
   | Ours |77.9 |57.1| 76.0 | 82.7 |61.1|
   |MacBERT-Large(SOTA)|88.9|70.0|-|-|-|
   
   Our model enjoys a high level of generation quality and accuracy, with 76% of generated answers containing the ground truth, which rivals the EM of span prediction SOTA. Our model has a lower EM because it generates complete sentences while golden answers are segmentations of sentences. The extremely high RougeL and BLEU-4 reveal the overlap between generated results and ground truth.
   P.S.The SOTA model only predicts the start and end tag as an extractive MRC task. 

   我们的模型有着极高的生成质量和准确率，76%的回答包含了正确答案(Contain Answer Rate)，和当前最好模型MacBERT-Large想媲美，它70%的起始位置预测和答案精确匹配(EM)。我们的模型EM值较低，因为生成的大部分为完整的句子，而标准答案通常是句子片段。
   P.S. SOTA模型只需预测起始和结束位置，这种抽取式阅读理解任务比生成式的简单很多。

## Cases

Here are random picked samples:
<img src="https://huggingface.co/IDEA-CCNL/Randeng-T5-784M-QA-Chinese/resolve/main/cases_t5_cmrc.png" div align=middle />

*pred:* in picture are generated results,*target* indicates groud truth.

If the picture fails to display, you can find the picture in Files and versions. 

## Usage
```python
import numpy as np
from transformers import T5Tokenizer,MT5ForConditionalGeneration

pretrain_path = 'IDEA-CCNL/Randeng-T5-784M-QA-Chinese'
tokenizer=T5Tokenizer.from_pretrained(pretrain_path)
model=MT5ForConditionalGeneration.from_pretrained(pretrain_path)

sample={"context":"在柏林,胡格诺派教徒创建了两个新的社区:多罗西恩斯塔特和弗里德里希斯塔特。到1700年,这个城市五分之一的人口讲法语。柏林胡格诺派在他们的教堂服务中保留了将近一个世纪的法语。他们最终决定改用德语,以抗议1806-1807年拿破仑占领普鲁士。他们的许多后代都有显赫的地位。成立了几个教会,如弗雷德里夏(丹麦)、柏林、斯德哥尔摩、汉堡、法兰克福、赫尔辛基和埃姆登的教会。","question":"除了多罗西恩斯塔特,柏林还有哪个新的社区?","idx":1}
plain_text='question:'+sample['question']+'knowledge:'+sample['context'][:self.max_knowledge_length]

res_prefix=tokenizer.encode('answer'+'<extra_id_0></s>',add_special_token=False)
l_rp=len(res_prefix)

tokenized=tokenizer.encode(plain_text,add_special_tokens=False,truncation=True,max_length=self.max_seq_length-2-l_rp)

tokenized+=res_prefix

# Generate answer
pred_ids = model.generate(input_ids=tokenized,max_new_token=self.max_target_length,do_sample=True,top_p=0.9)
tokenizer.batch_decode(pred_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
```


# Citation

You can also cite our [website](https://github.com/IDEA-CCNL/Fengshenbang-LM/):

欢迎引用我们的[网站](https://github.com/IDEA-CCNL/Fengshenbang-LM/):
```text
@misc{Fengshenbang-LM,
  title={Fengshenbang-LM},
  author={IDEA-CCNL},
  year={2021},
  howpublished={\url{https://github.com/IDEA-CCNL/Fengshenbang-LM}},
}
```