Improving Generalization in Language Model-Based Text-to-SQL Semantic Parsing: Two Simple Semantic Boundary-Based Techniques

Daking Rai, Bailin Wang, Yilun Zhou, Ziyu Yao
5/27/2023
cs.CLcs.AI

No official code found. Best implementation: Dakingrai/ood-generalization-semantic-boundary-techniques (12 stars, MIT, last commit 2024-11-17).

Abstract

Compositional and domain generalization present significant challenges in semantic parsing, even for state-of-the-art semantic parsers based on pre-trained language models (LMs). In this study, we empirically investigate improving an LM's generalization in semantic parsing with two simple techniques: at the token level, we introduce a token preprocessing method to preserve the semantic boundaries of tokens produced by LM tokenizers; at the sequence level, we propose to use special tokens to mark the boundaries of components aligned between input and output. Our experimental results on two text-to-SQL semantic parsing datasets show that our token preprocessing, although simple, can substantially improve the LM performance on both types of generalization, and our component boundary marking method is particularly helpful for compositional generalization.

View on arXivView PDF

Code Implementations(1)

Dakingrai/ood-generalization-semantic-boundary-techniquesCommunity100%
MIT
122PythonMay 11, 20231 years agoMIT

Similar Papers

Compositional Generalization without Trees using Multiset Tagging and Latent Permutations

86% match2023

ReCOGS: How Incidental Details of a Logical Form Overshadow an Evaluation of Semantic Interpretation

84% match1 repo102023

SLOG: A Structural Generalization Benchmark for Semantic Parsing

83% match1 repo72023

Adapt and Decompose: Efficient Generalization of Text-to-SQL via Domain Adapted Least-To-Most Prompting

83% match2023

Towards Compositionally Generalizable Semantic Parsing in Large Language Models: A Survey

83% match2024

Laziness Is a Virtue When It Comes to Compositionality in Neural Semantic Parsing

82% match2023

Cite this paper

@article{rai2023improving,
  title  = {Improving Generalization in Language Model-Based Text-to-SQL Semantic Parsing: Two Simple Semantic Boundary-Based Techniques},
  author = {Daking Rai and Bailin Wang and Yilun Zhou and Ziyu Yao},
  year   = {2023},
  eprint = {2305.17378},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2305.17378v1}
}

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/2305.17378.svg)](https://codeofpaper.com/paper/2305.17378)

Discussion