Learning Semantic Structure through First-Order-Logic Translation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chaturvedi, Akshay, Asher, Nicholas
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910632610103296
author Chaturvedi, Akshay
Asher, Nicholas
author_facet Chaturvedi, Akshay
Asher, Nicholas
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_03203
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning Semantic Structure through First-Order-Logic Translation
Chaturvedi, Akshay
Asher, Nicholas
Computation and Language
Machine Learning
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.
title Learning Semantic Structure through First-Order-Logic Translation
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2410.03203