模型:
microsoft/tapex-large-finetuned-wtq
TAPEX是由刘前,陈贝,郭佳琪,Morteza Ziyadi,林泽琪,陈伟柱,楼建光于 TAPEX: Table Pre-training via Learning a Neural SQL Executor 提出的。原始代码库可以在 here 中找到。
TAPEX(Table Pre-training via Execution)是一种概念简单且经验丰富的预训练方法,可以赋予现有模型具有表格推理技能。TAPEX通过学习一个神经SQL执行器来实现表格预训练,该执行器通过自动合成可执行的SQL查询获取合成语料库。
TAPEX基于BART架构,具有双向(类BERT)编码器和自回归(类GPT)解码器的Transformer编码器-解码器(seq2seq)模型。
此模型是在 WikiTableQuestions 数据集上微调的tapex-base模型。
您可以使用该模型回答关于复杂问题的表格问答。下面显示了一些可解答的问题(对应的表格未显示):
| Question | Answer | 
|---|---|
| according to the table, what is the last title that spicy horse produced? | Akaneiro: Demon Hunters | 
| what is the difference in runners-up from coleraine academical institution and royal school dungannon? | 20 | 
| what were the first and last movies greenstreet acted in? | The Maltese Falcon, Malaya | 
| in which olympic games did arasay thondike not finish in the top 20? | 2012 | 
| which broadcaster hosted 3 titles but they had only 1 episode? | Channel 4 | 
这里是在transformers中使用此模型的方法:
from transformers import TapexTokenizer, BartForConditionalGeneration
import pandas as pd
tokenizer = TapexTokenizer.from_pretrained("microsoft/tapex-large-finetuned-wtq")
model = BartForConditionalGeneration.from_pretrained("microsoft/tapex-large-finetuned-wtq")
data = {
    "year": [1896, 1900, 1904, 2004, 2008, 2012],
    "city": ["athens", "paris", "st. louis", "athens", "beijing", "london"]
}
table = pd.DataFrame.from_dict(data)
# tapex accepts uncased input since it is pre-trained on the uncased corpus
query = "In which year did beijing host the Olympic Games?"
encoding = tokenizer(table=table, query=query, return_tensors="pt")
outputs = model.generate(**encoding)
print(tokenizer.batch_decode(outputs, skip_special_tokens=True))
# [' 2008.0']
 请找到评估脚本 here 。
@inproceedings{
    liu2022tapex,
    title={{TAPEX}: Table Pre-training via Learning a Neural {SQL} Executor},
    author={Qian Liu and Bei Chen and Jiaqi Guo and Morteza Ziyadi and Zeqi Lin and Weizhu Chen and Jian-Guang Lou},
    booktitle={International Conference on Learning Representations},
    year={2022},
    url={https://openreview.net/forum?id=O50443AsCP}
}