Conference Papers Year : 2024

Learning Semantic Structure through First-Order-Logic Translation

Abstract

In this paper, we study whether transformerbased 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.

Fichier principal
Vignette du fichier
emnlp-1-1.pdf (245) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04829344 , version 1 (10-12-2024)

Identifiers

  • HAL Id : hal-04829344 , version 1

Cite

Akshay Chaturvedi, Nicholas Asher. Learning Semantic Structure through First-Order-Logic Translation. EMNLP2024, Association for Computational Linguistics, Nov 2024, Miami (FL), United States. pp.6669-6680. ⟨hal-04829344⟩
28 View
4 Download

Share

More