Leveraging Code to Improve In-context Learning for Semantic Parsing

arXiv:2311.09519v2 Announce Type: replace
Abstract: In-context learning (ICL) is an appealing approach for semantic parsing due to its few-shot nature and improved generalization. However, learning to parse to rare domain-specific languages (DSLs) from just a few demonstrations is challenging, limiting the performance of even the most capable LLMs. In this work, we improve the effectiveness of ICL for semantic parsing by (1) using general-purpose programming languages such as Python instead of DSLs, and (2) augmenting prompts with a structured domain …

abstract arxiv code context cs.cl domain few-shot however in-context learning languages llms nature parsing performance semantic type work