Retrieval-Augmented Semantic Parsing: Improving Generalization with Lexical Knowledge
This addresses the problem of generalization in semantic parsing for AI systems, representing a strong specific gain rather than a foundational breakthrough.
The paper tackled the challenge of open-domain semantic parsing by introducing Retrieval-Augmented Semantic Parsing (RASP), which integrates external symbolic knowledge, and found that it nearly doubled performance on out-of-distribution concepts compared to previous models.
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.