|
--- |
|
language: en |
|
tags: |
|
- tapex |
|
- table-question-answering |
|
license: mit |
|
--- |
|
|
|
# TAPEX (base-sized model) |
|
|
|
TAPEX was proposed in [TAPEX: Table Pre-training via Learning a Neural SQL Executor](https://arxiv.org/abs/2107.07653) by Qian Liu, Bei Chen, Jiaqi Guo, Morteza Ziyadi, Zeqi Lin, Weizhu Chen, Jian-Guang Lou. The original repo can be found [here](https://github.com/microsoft/Table-Pretraining). |
|
|
|
## Model description |
|
|
|
TAPEX (**Ta**ble **P**re-training via **Ex**ecution) is a conceptually simple and empirically powerful pre-training approach to empower existing models with *table reasoning* skills. TAPEX realizes table pre-training by learning a neural SQL executor over a synthetic corpus, which is obtained by automatically synthesizing executable SQL queries. |
|
|
|
TAPEX is based on the BART architecture, the transformer encoder-encoder (seq2seq) model with a bidirectional (BERT-like) encoder and an autoregressive (GPT-like) decoder. |
|
|
|
## Intended Uses |
|
|
|
You can use the raw model for simulating neural SQL execution, i.e., employ TAPEX to execute a SQL query on a given table. However, the model is mostly meant to be fine-tuned on a supervised dataset. Currently TAPEX can be fine-tuned to tackle table question answering tasks and table fact verification tasks. See the [model hub](https://huggingface.co/models?search=tapex) to look for fine-tuned versions on a task that interests you. |
|
|
|
### How to Use |
|
|
|
Here is how to use this model in transformers: |
|
|
|
```python |
|
from transformers import TapexTokenizer, BartForConditionalGeneration |
|
import pandas as pd |
|
|
|
tokenizer = TapexTokenizer.from_pretrained("microsoft/tapex-base") |
|
model = BartForConditionalGeneration.from_pretrained("microsoft/tapex-base") |
|
|
|
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 = "select year where city = beijing" |
|
encoding = tokenizer(table=table, query=query, return_tensors="pt") |
|
|
|
outputs = model.generate(**encoding) |
|
|
|
print(tokenizer.batch_decode(outputs, skip_special_tokens=True)) |
|
# ['2008'] |
|
``` |
|
|
|
### How to Fine-tuning |
|
|
|
Please find the fine-tuning script [here](https://github.com/SivilTaram/transformers/tree/add_tapex_bis/examples/research_projects/tapex). |
|
|
|
### BibTeX entry and citation info |
|
|
|
```bibtex |
|
@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} |
|
} |
|
``` |
