omnitab-large / README.md
Zhengbao Jiang
init commit
7776a74
---
language: en
tags:
- tapex
- table-question-answering
datasets:
- wikitablequestions
---
# OmniTab
OmniTab is a table-based QA model proposed in [OmniTab: Pretraining with Natural and Synthetic Data for Few-shot Table-based Question Answering](https://arxiv.org/pdf/2207.03637.pdf). The original Github repository is [https://github.com/jzbjyb/OmniTab](https://github.com/jzbjyb/OmniTab).
## Description
`neulab/omnitab-large` (based on BART architecture) is initialized with `microsoft/tapex-large` and continuously pretrained on natural and synthetic data.
## Usage
```python
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import pandas as pd
tokenizer = AutoTokenizer.from_pretrained("neulab/omnitab-large")
model = AutoModelForSeq2SeqLM.from_pretrained("neulab/omnitab-large")
data = {
"year": [1896, 1900, 1904, 2004, 2008, 2012],
"city": ["athens", "paris", "st. louis", "athens", "beijing", "london"]
}
table = pd.DataFrame.from_dict(data)
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']
```
## Reference
```bibtex
@inproceedings{jiang-etal-2022-omnitab,
title = "{O}mni{T}ab: Pretraining with Natural and Synthetic Data for Few-shot Table-based Question Answering",
author = "Jiang, Zhengbao and Mao, Yi and He, Pengcheng and Neubig, Graham and Chen, Weizhu",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
}
```