Tasks

Table Question Answering

Table Question Answering (Table QA) is the answering a question about an information on a given table.

Inputs
Rank Name No.of reigns Combined days
1 lou Thesz 3 3749
2 Ric Flair 8 3103
3 Harley Race 7 1799
Question

What is the number of reigns for Harley Race?

Table Question Answering Model
Output
Result

7

About Table Question Answering

Use Cases

SQL execution

You can use the Table Question Answering models to simulate SQL execution by inputting a table.

Table Question Answering

Table Question Answering models are capable of answering questions based on a table.

Task Variants

This place can be filled with variants of this task if there's any.

Inference

You can infer with TableQA models using the 🤗 Transformers library.

from transformers import pipeline
import pandas as pd

# prepare table + question
data = {"Actors": ["Brad Pitt", "Leonardo Di Caprio", "George Clooney"], "Number of movies": ["87", "53", "69"]}
table = pd.DataFrame.from_dict(data)
question = "how many movies does Leonardo Di Caprio have?"

# pipeline model
# Note: you must to install torch-scatter first.
tqa = pipeline(task="table-question-answering", model="google/tapas-large-finetuned-wtq")

# result

print(tqa(table=table, query=query)['cells'][0])
#53

Useful Resources

In this area, you can insert useful resources about how to train or use a model for this task.

This task page is complete thanks to the efforts of Hao Kim Tieu. 🦸

Compatible libraries

Table Question Answering demo
s
This model can be loaded on the Inference API on-demand.
Models for Table Question Answering
Browse Models (77)

Note A table question answering model that is capable of neural SQL execution, i.e., employ TAPEX to execute a SQL query on a given table.

Datasets for Table Question Answering
Browse Datasets (126)

Note The WikiTableQuestions dataset is a large-scale dataset for the task of question answering on semi-structured tables.

Note WikiSQL is a dataset of 80654 hand-annotated examples of questions and SQL queries distributed across 24241 tables from Wikipedia.

Spaces using Table Question Answering

Note An application that answers questions based on table CSV files.

Metrics for Table Question Answering
Denotation Accuracy
Checks whether the predicted answer(s) is the same as the ground-truth answer(s).