Compositional Semantic Parsing on Semi-Structured Tables

Panupong Pasupat, Percy Liang
8/3/2015
cs.CL

Official code: percyliang/sempre (842 stars, last commit 2023-05-01).

Abstract

Two important aspects of semantic parsing for question answering are the breadth of the knowledge source and the depth of logical compositionality. While existing work trades off one aspect for another, this paper simultaneously makes progress on both fronts through a new task: answering complex questions on semi-structured tables using question-answer pairs as supervision. The central challenge arises from two compounding factors: the broader domain results in an open-ended set of relations, and the deeper compositionality results in a combinatorial explosion in the space of logical forms. We propose a logical-form driven parsing algorithm guided by strong typing constraints and show that it obtains significant improvements over natural baselines. For evaluation, we created a new dataset of 22,033 complex questions on Wikipedia tables, which is made publicly available.

View on arXivView PDF

Code Implementations(1)

percyliang/sempreOfficial100%

Semantic Parser with Execution

842293CSS, HTMLSep 18, 20133 years agoNOASSERTION

Similar Papers

TAPAS: Weakly Supervised Table Parsing via Pre-training

86% match1 repo1.2k2020

The Web as a Knowledge-base for Answering Complex Questions

86% match1 repo782018

Semantic Decomposition of Question and SQL for Text-to-SQL Parsing

85% match1 repo62023

Semantic Parsing with Candidate Expressions for Knowledge Base Question Answering

84% match1 repo2024

API-Assisted Code Generation for Question Answering on Varied Table Structures

83% match2023

Semantic Parsing for Conversational Question Answering over Knowledge Graphs

82% match1 repo192023

Cite this paper

@article{pasupat2015compositional,
  title  = {Compositional Semantic Parsing on Semi-Structured Tables},
  author = {Panupong Pasupat and Percy Liang},
  year   = {2015},
  eprint = {1508.00305},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1508.00305}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1508.00305.svg)](https://codeofpaper.com/paper/1508.00305)

Discussion