Towards Universal Semantics With Large Language Models
This work addresses the slow, manual process of creating semantic paraphrases for NLP tasks like semantic analysis and translation, representing an incremental improvement by applying existing LLM methods to a new domain.
The authors tackled the problem of manually generating Natural Semantic Metalanguage (NSM) explications by using large language models (LLMs) to automate the process, resulting in 1B and 8B models that outperform GPT-4o in producing accurate, cross-translatable explications.
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.