TAPEX（大型模型）

TAPEX是由 Qian Liu、Bei Chen、Jiaqi Guo、Morteza Ziyadi、Zeqi Lin、Weizhu Chen、Jian-Guang Lou 于 TAPEX: Table Pre-training via Learning a Neural SQL Executor 年提出的。原始存储库可在 here 找到。

模型描述

TAPEX（表格预训练通过执行）是一种概念简单、经验证明强大的预训练方法，用于赋予现有模型表格推理能力。TAPEX通过学习一个在合成语料库上执行SQL查询的神经网络SQL执行器来实现表格预训练，合成语料库是通过自动合成可执行的SQL查询获得的。

TAPEX基于BART架构，是一种转换器编码器-编码器（seq2seq）模型，具有双向（类似BERT）编码器和自回归（类似GPT）解码器。

该模型是在 WikiSQL 数据集上微调的 tapex-base 模型。

预期用途

您可以在相对简单的问题上使用该模型进行表格问答。以下是一些可解决的问题示例（对应的表格暂未显示）：

Question	Answer
tell me what the notes are for south australia	no slogan on current series
what position does the player who played for butler cc (ks) play?	guard-forward
how many schools did player number 3 play at?	1.0
how many winning drivers in the kraco twin 125 (r2) race were there?	1.0
for the episode(s) aired in the u.s. on 4 april 2008, what were the names?	"bust a move" part one, "bust a move" part two

如何使用

以下是在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-wikisql")
model = BartForConditionalGeneration.from_pretrained("microsoft/tapex-large-finetuned-wikisql")

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']

如何评估

请查找评估脚本 here 。

BibTeX条目和引用信息

@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}
}

作者:

Microsoft

数据集大小:

3.03 GB