FOL2NS generates synthetic first-order logic formulas with varying quantifier depths and translates them into natural language sentences via a hybrid rule-driven and fine-tuned language model approach.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , pages =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
FOL2NS: Generating Natural Sentences from First-Order Logic
FOL2NS generates synthetic first-order logic formulas with varying quantifier depths and translates them into natural language sentences via a hybrid rule-driven and fine-tuned language model approach.