0

Constrained Language Models Yield Few-Shot Semantic Parsers

Using large pretrained language models to paraphrase input into an English-like controlled sublanguage enhances few-shot semantic parsing performance significantly.

Year
2021
Venue
EMNLP 2021 11
Authors
10
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2104.08768v2ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

We explore the use of large pretrained language models as few-shot semantic parsers. The goal in semantic parsing is to generate a structured meaning representation given a natural language input. However, language models are trained to generate natural language. To bridge the gap, we use language models to paraphrase inputs into a controlled sublanguage resembling English that can be automatically mapped to a target meaning representation. Our results demonstrate that with only a small amount of data and very little code to convert into English-like representations, our blueprint for rapidly bootstrapping semantic parsers leads to surprisingly effective performance on multiple community tasks, greatly exceeding baseline methods also trained on the same limited data.

Authors

10