用大模型自动生成跨语言语义素，让复杂概念可通用解析
Towards Universal Semantics With Large Language Models
- 用大模型自动生成基于语义素的词语解释，替代人工逐个分析
- 10亿和80亿参数模型比GPT-4o更准确地生成跨语言可译的解释
- 适合做语义分析、机器翻译等需要统一语义表示的任务
自然语义元语言（NSM）是一种基于普遍语义素的语言理论，这些语义素是简单、原始的词义单位，在世界绝大多数语言中都存在。根据该框架，任何词语，无论多复杂，均可通过这些语义素进行释义，揭示清晰且普遍可翻译的意义。此类释义称为‘解释’（explications），在自然语言处理中具有重要应用价值，但传统上需人工缓慢完成。本文首次研究使用大语言模型（LLMs）生成NSM解释，提出自动评估方法、专用训练与评测数据集，并微调出对应模型。1B和8B参数模型在生成准确、跨语言可译解释方面优于GPT-4o，标志着迈向通用语义表征的重要一步，为语义分析、翻译等任务开辟新可能。代码已开源：https://github.com/OSU-STARLAB/DeepNSM。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。