Tapex-large Open-source Table Reasoning Model - Empowering Table Reasoning Tasks Based on BART Architecture

Tapex Large

Developed by microsoft

TAPEX is a model designed for table reasoning tasks, learning through neural SQL executors for table pretraining, based on the BART architecture.

Large Language Model

Transformers

EnglishOpen Source License:MIT #Table Reasoning #SQL Execution Pretraining #BART Architecture

Downloads 252

Release Time : 3/10/2022

Model Overview

TAPEX achieves table pretraining by learning neural SQL executors on a synthetic corpus, aiming to endow the model with table reasoning capabilities. The model is based on the BART architecture, combining a bidirectional encoder and an autoregressive decoder.

Model Features

Table Pretraining

Achieves table pretraining through neural SQL executor learning, enhancing the model's reasoning capabilities on tabular data.

BART Architecture

A Transformer architecture combining bidirectional encoders and autoregressive decoders, suitable for sequence-to-sequence tasks.

SQL Execution Capability

Capable of understanding and executing SQL queries, suitable for complex tabular data operations and analysis.

Model Capabilities

Table Data Understanding

SQL Query Execution

Table Question Answering

Table Reasoning

Use Cases

Data Analysis

Table Question Answering System

Builds systems capable of answering natural language questions based on tabular data.

Improves question answering accuracy and efficiency.

Automated Data Querying

Converts natural language queries into SQL queries and executes them, simplifying the data querying process.

Reduces the need for manual SQL query writing.

🚀 TAPEX (large-sized model)

TAPEX is a pre - training approach that endows existing models with table reasoning skills. It was proposed in a research paper, offering a new solution for table - related tasks.

✨ Features

TAPEX (Table Pre - training via Execution) is a conceptually simple and empirically powerful pre - training approach. It empowers 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. It is based on the BART architecture, a transformer encoder - encoder (seq2seq) model with a bidirectional (BERT - like) encoder and an autoregressive (GPT - like) decoder.

📚 Documentation

TAPEX was proposed in TAPEX: Table Pre - training via Learning a Neural SQL Executor 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).

Intended Uses

⚠️ Important Note

This model checkpoint is ONLY used for fine - tuining on downstream tasks, and you CANNOT use this model for simulating neural SQL execution, i.e., employ TAPEX to execute a SQL query on a given table. The one that can neurally execute SQL queries is at [here](https://huggingface.co/microsoft/tapex - large - sql - execution).

💡 Usage Tip

This separation of two models for two kinds of intention is because of a known issue in BART large, and we recommend readers to see [this comment](https://github.com/huggingface/transformers/issues/15559#issuecomment - 1062880564) for more details.

How to Fine - tuning

Please find the fine - tuning 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