Towards Universal Semantics With Large Language Models

TL;DR

This paper explores using large language models to generate Natural Semantic Metalanguage explications, aiming to establish a universal semantic framework applicable across languages and NLP tasks.

Contribution

It introduces the first automated approach using LLMs for NSM explication, including datasets, evaluation methods, and fine-tuned models surpassing GPT-4o.

Findings

Fine-tuned models outperform GPT-4o in accuracy

Automated methods enable scalable NSM explication

Potential applications in semantic analysis and translation

Abstract

The Natural Semantic Metalanguage (NSM) is a linguistic theory based on a universal set of semantic primes: simple, primitive word-meanings that have been shown to exist in most, if not all, languages of the world. According to this framework, any word, regardless of complexity, can be paraphrased using these primes, revealing a clear and universally translatable meaning. These paraphrases, known as explications, can offer valuable applications for many natural language processing (NLP) tasks, but producing them has traditionally been a slow, manual process. In this work, we present the first study of using large language models (LLMs) to generate NSM explications. We introduce automatic evaluation methods, a tailored dataset for training and evaluation, and fine-tuned models for this task. Our 1B and 8B models outperform GPT-4o in producing accurate, cross-translatable explications, marking a significant step toward universal semantic representation with LLMs and opening up new possibilities for applications in semantic analysis, translation, and beyond. Our code is available at https://github.com/OSU-STARLAB/DeepNSM.