MixQG（基础尺寸模型）

MixQG是一个新的问题生成模型，它在一系列包含不同类型答案的QA数据集上进行了预训练。该模型在论文 MixQG: Neural Question Generation with Mixed Answer Types 中进行了介绍，相关代码已经在 this 的存储库中发布。

如何使用

使用Huggingface的管道抽象：

from transformers import pipeline

nlp = pipeline("text2text-generation", model='Salesforce/mixqg-base', tokenizer='Salesforce/mixqg-base')
    
CONTEXT = "In the late 17th century, Robert Boyle proved that air is necessary for combustion."
ANSWER = "Robert Boyle"

def format_inputs(context: str, answer: str):
    return f"{answer} \\n {context}"

text = format_inputs(CONTEXT, ANSWER)

nlp(text)
# should output [{'generated_text': 'Who proved that air is necessary for combustion?'}]

直接使用预训练模型：

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained('Salesforce/mixqg-base')
model = AutoModelForSeq2SeqLM.from_pretrained('Salesforce/mixqg-base')

CONTEXT = "In the late 17th century, Robert Boyle proved that air is necessary for combustion."
ANSWER = "Robert Boyle"

def format_inputs(context: str, answer: str):
    return f"{answer} \\n {context}"

text = format_inputs(CONTEXT, ANSWER)

input_ids = tokenizer(text, return_tensors="pt").input_ids
generated_ids = model.generate(input_ids, max_length=32, num_beams=4)
output = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
print(output)
# should output "Who proved that air is necessary for combustion?"

引用

@misc{murakhovska2021mixqg,
      title={MixQG: Neural Question Generation with Mixed Answer Types}, 
      author={Lidiya Murakhovs'ka and Chien-Sheng Wu and Tong Niu and Wenhao Liu and Caiming Xiong},
      year={2021},
      eprint={2110.08175},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}