|
--- |
|
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-128shot` (based on BART architecture) is initialized with `microsoft/tapex-large` and continuously pretrained on natural and synthetic data (SQL2NL model trained in the 128-shot setting). |
|
|
|
## Usage |
|
|
|
```python |
|
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM |
|
import pandas as pd |
|
|
|
tokenizer = AutoTokenizer.from_pretrained("neulab/omnitab-large-128shot") |
|
model = AutoModelForSeq2SeqLM.from_pretrained("neulab/omnitab-large-128shot") |
|
|
|
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", |
|
} |
|
``` |
|
|
