SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.08768 · EMNLP · 2021

Constrained Language Models Yield Few-Shot Semantic Parsers

Dan Klein, Jason Eisner, Richard Shin, Subhro Roy, Sam Thomson, Adam Pauls, Benjamin Van Durme, Charles Chen, Christopher Lin, Antonios Platanios

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

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.

For agents

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

get_harvested_code_for_paper("2104.08768")
get_code_for_paper("2104.08768")
have("2104.08768")

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

curl https://syntology.ai/api/ran/2104.08768.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.08768.svg)](https://syntology.ai/paper/2104.08768)

Connect an agent — have() is free.