Our paper “Language Models as Controlled Natural Language Semantic Parsers for Knowledge Graph Question Answering” got accepted at #ecai2023. It shows that LLMs can learn controlled natural language with fine-tuning on limited training data. Details on our findings are here: https://amazon.science/publications/language-models-as-controlled-natural-language-semantic-parsers-for-knowledge-graph-question-answering
@amazon @SaharVahdati Preetam Gattogi, Dhananjay Bhandiwad Sébastien Ferré #LLM #KnowledgeGraphs