Saved in:
Bibliographic Details
Main Authors: Zhang, Xiao, Meng, Qianru, Bos, Johan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.10207
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915452302655488
author Zhang, Xiao
Meng, Qianru
Bos, Johan
author_facet Zhang, Xiao
Meng, Qianru
Bos, Johan
contents Open-domain semantic parsing remains a challenging task, as neural models often rely on heuristics and struggle to handle unseen concepts. In this paper, we investigate the potential of large language models (LLMs) for this task and introduce Retrieval-Augmented Semantic Parsing (RASP), a simple yet effective approach that integrates external symbolic knowledge into the parsing process. Our experiments not only show that LLMs outperform previous encoder-decoder baselines for semantic parsing, but that RASP further enhances their ability to predict unseen concepts, nearly doubling the performance of previous models on out-of-distribution concepts. These findings highlight the promise of leveraging large language models and retrieval mechanisms for robust and open-domain semantic parsing.
format Preprint
id arxiv_https___arxiv_org_abs_2412_10207
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Retrieval-Augmented Semantic Parsing: Improving Generalization with Lexical Knowledge
Zhang, Xiao
Meng, Qianru
Bos, Johan
Computation and Language
Open-domain semantic parsing remains a challenging task, as neural models often rely on heuristics and struggle to handle unseen concepts. In this paper, we investigate the potential of large language models (LLMs) for this task and introduce Retrieval-Augmented Semantic Parsing (RASP), a simple yet effective approach that integrates external symbolic knowledge into the parsing process. Our experiments not only show that LLMs outperform previous encoder-decoder baselines for semantic parsing, but that RASP further enhances their ability to predict unseen concepts, nearly doubling the performance of previous models on out-of-distribution concepts. These findings highlight the promise of leveraging large language models and retrieval mechanisms for robust and open-domain semantic parsing.
title Retrieval-Augmented Semantic Parsing: Improving Generalization with Lexical Knowledge
topic Computation and Language
url https://arxiv.org/abs/2412.10207