Open-source Tapex-base-finetuned-wikisql model - Free to use for table question-answering tasks, accurately answer questions

Tapex Base Finetuned Wikisql

Developed by microsoft

TAPEX is a model designed for table question answering tasks, learning table pre-training through neural SQL executors and based on the BART architecture.

Question Answering System

Transformers

EnglishOpen Source License:MIT #Table Question Answering #SQL Execution Pretraining #Structured Data Reasoning

Downloads 242

Release Time : 3/2/2022

Model Overview

TAPEX achieves table pre-training by learning neural SQL executors on a synthetic corpus, endowing the model with table reasoning capabilities. The model is fine-tuned on the WikiSQL dataset.

Model Features

Table Reasoning Capability

Achieves table pre-training by learning neural SQL executors, endowing the model with powerful table reasoning capabilities.

Based on BART Architecture

Adopts the BART architecture, combining the advantages of bidirectional encoders and autoregressive decoders.

Simple and Efficient

Conceptually simple yet empirically powerful, suitable for relatively straightforward table question answering tasks.

Model Capabilities

Table Question Answering

Table Reasoning

SQL Query Execution

Use Cases

Table Question Answering

Querying Table Data

Answer simple questions about table data, such as querying information for a specific year or city.

For example, querying 'In which year did Beijing host the Olympics?' returns '2008.0'.

Summarizing Table Data

Perform statistical operations on table data, such as calculating the average or sum of a column.

For example, querying 'How many schools has player No. 3 attended?' returns '1.0'.

🚀 TAPEX (base-sized model)

TAPEX is a pre - training approach that endows existing models with table reasoning skills. It was proposed in a research paper and can be used for table question - answering tasks.

✨ Features

TAPEX is a conceptually simple and empirically powerful pre - training approach for table reasoning.
It is based on the BART architecture, a transformer encoder - encoder (seq2seq) model.
This tapex - base model is fine - tuned on the WikiSQL dataset.

📦 Installation

No installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

from transformers import TapexTokenizer, BartForConditionalGeneration
import pandas as pd

tokenizer = TapexTokenizer.from_pretrained("microsoft/tapex-base-finetuned-wikisql")
model = BartForConditionalGeneration.from_pretrained("microsoft/tapex-base-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']

📚 Documentation

Model description

TAPEX (Table Pre - training via Execution) 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.

This model is the tapex - base model fine - tuned on the WikiSQL dataset.

Intended Uses

You can use the model for table question answering on relatively simple questions. Some solveable questions are shown below (corresponding tables now shown):

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

How to Eval

Please find the eval script here.

BibTeX entry and citation info

@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}
}

📄 License

This project is licensed under the MIT license.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご