English

Learning Semantic Structure through First-Order-Logic Translation

Computation and Language 2024-10-07 v1 Machine Learning

Abstract

In this paper, we study whether transformer-based language models can extract predicate argument structure from simple sentences. We firstly show that language models sometimes confuse which predicates apply to which objects. To mitigate this, we explore two tasks: question answering (Q/A), and first order logic (FOL) translation, and two regimes, prompting and finetuning. In FOL translation, we finetune several large language models on synthetic datasets designed to gauge their generalization abilities. For Q/A, we finetune encoder models like BERT and RoBERTa and use prompting for LLMs. The results show that FOL translation for LLMs is better suited to learn predicate argument structure.

Keywords

Cite

@article{arxiv.2410.03203,
  title  = {Learning Semantic Structure through First-Order-Logic Translation},
  author = {Akshay Chaturvedi and Nicholas Asher},
  journal= {arXiv preprint arXiv:2410.03203},
  year   = {2024}
}

Comments

EMNLP 2024 Findings

R2 v1 2026-06-28T19:08:11.532Z