Compositional Semantic Parsing on Semi-Structured Tables

Launch Dataset Viewer Download Dataset Official Evaluator

Please see the usage notes below!

Note: The dataset viewer contains training data from dataset version 1.0.2


Task

Answer complex questions on semi-structured tables using question-answer pairs as supervision.

Why this task?

We want to solve the two main challenges of question answering:

Instead of approaching one challenge at a time, we want to handle both simultaneously:

Usage Notes

Please use the latest version (1.0.2) and the official evaluator for future development.

The dataset splits used in the original paper are:

The file pristine-seen-tables.tsv was not used in the original paper.

Paper, Code, and Reproducible Experiments

Panupong Pasupat, Percy Liang. Compositional Semantic Parsing on Semi-Structured Tables. Association for Computational Linguistics (ACL), 2015.

The paper proposes a semantic parsing system that learns to answer questions using question-answer pairs as supervision.

Code, data, and experiments are available on the CodaLab platform.

The code is implemented in SEMPRE framework.

Other Material and Related Work