What libraries can I use for Table Question Answering?

The and transformers library is compatible with Table Question Answering.

What models can I use for Table Question Answering?

The microsoft/tapex-baseand google/tapas-base-finetuned-wtq models can be used for Table Question Answering.

What datasets can I use for Table Question Answering?

The wikitablequestionsand wikisql datasets can be used for Table Question Answering.

What metrics can I use for Table Question Answering?

The and Denotation Accuracy metric can be used for Table Question Answering.

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

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