ReasTAP

ReasTAP is a table reasoning model proposed in the EMNLP 2022 paper ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples. The original Github repository is https://github.com/Yale-LILY/ReasTAP.

Description

Yale-LILY/reastap-large-finetuned-wtq is initialized with Yale-LILY/reastap-large and finetuned on WikiTableQuestions.

Usage

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import pandas as pd

tokenizer = AutoTokenizer.from_pretrained("Yale-LILY/reastap-large-finetuned-wtq")
model = AutoModelForSeq2SeqLM.from_pretrained("Yale-LILY/reastap-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)

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

@inproceedings{zhao-etal-2022-reastap,
    title = "{R}eas{TAP}: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples",
    author = "Zhao, Yilun  and
      Nan, Linyong  and
      Qi, Zhenting  and
      Zhang, Rui  and
      Radev, Dragomir",
    booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.emnlp-main.615",
    pages = "9006--9018",
    abstract = "Reasoning over tabular data requires both table structure understanding and a broad set of table reasoning skills. Current models with table-specific architectures and pre-training methods perform well on understanding table structures, but they still struggle with tasks that require various table reasoning skills. In this work, we develop ReasTAP to show that high-level table reasoning skills can be injected into models during pre-training without a complex table-specific architecture design. We define 7 table reasoning skills, such as numerical operation, temporal comparison, and conjunction. Each reasoning skill is associated with one example generator, which synthesizes questions over semi-structured tables according to the sampled templates. We model the table pre-training task as a sequence generation task and pre-train ReasTAP to generate precise answers of the synthetic examples. ReasTAP is evaluated on four benchmarks covering three downstream tasks including 1) WikiSQL-Weak and WikiTQ for Table Question Answering, 2) TabFact for Table Fact Verification, and 3) LogicNLG for Faithful Table-to-Text Generation. Experimental results demonstrate that ReasTAP achieves new state-of-the-art results on all of them and delivers a significant improvement under low-resource setting. Our code is publicly available at https://github.com/Yale-LILY/ReasTAP.",
}
Downloads last month
19
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train Yale-LILY/reastap-large-finetuned-wtq