Towards Compositionally Generalizable Semantic Parsing in Large Language Models: A Survey

arXiv:2404.13074v1 Announce Type: new
Abstract: Compositional generalization is the ability of a model to generalize to complex, previously unseen types of combinations of entities from just having seen the primitives. This type of generalization is particularly relevant to the semantic parsing community for applications such as task-oriented dialogue, text-to-SQL parsing, and information retrieval, as they can harbor infinite complexity. Despite the success of large language models (LLMs) in a wide range of NLP tasks, unlocking perfect compositional generalization still remains …

abstract applications arxiv community cs.ai cs.cl dialogue language language models large language large language models parsing semantic sql survey text text-to-sql type types