SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.10540 · ACL Findings · 2021

Awakening Latent Grounding from Pretrained Language Models for Semantic Parsing

Qian Liu, Jian-Guang Lou, Bin Zhou, Jiaqi Guo, Jiahui Zhang, Dejian Yang

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recent years pretrained language models (PLMs) hit a success on several downstream tasks, showing their power on modeling language. To better understand and leverage what PLMs have learned, several techniques have emerged to explore syntactic structures entailed by PLMs. However, few efforts have been made to explore grounding capabilities of PLMs, which are also essential. In this paper, we highlight the ability of PLMs to discover which token should be grounded to which concept, if combined with our proposed erasingthen-awakening approach. Empirical studies on four datasets demonstrate that our approach can awaken latent grounding which is understandable to human experts, even if it is not exposed to such labels during training. More importantly, our approach shows great potential to benefit downstream semantic parsing models. Taking text-to-SQL as a case study, we successfully couple our approach with two off-the-shelf parsers, obtaining an absolute improvement of up to 9.8%.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2109.10540")
get_code_for_paper("2109.10540")
have("2109.10540")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2109.10540.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2109.10540.svg)](https://syntology.ai/paper/2109.10540)

Connect an agent — have() is free.