让非专家用自然语言查询词典知识图谱，提升可访问性。
Conversational Lexicography: Querying Lexicographic Data on Knowledge Graphs with SPARQL through Natural Language
- 构建四维词典本体分类体系，生成超120万条自然语言到SPARQL的映射
- GPT-3.5-Turbo在陌生模式下仍能有效推理，其他模型表现有限
- 适合词典学研究者、语言数据工程师使用，推动开放词典数据应用
知识图谱为表示词典语义结构提供了优秀方案，但SPARQL查询语言对非专业用户仍是重大障碍。本文针对维基数据等知识图谱上的词典数据检索，提出自然语言接口解决方案。我们构建了涵盖四个维度的多维分类体系，刻画维基数据词典本体模块的复杂性，并创建了一个包含超过120万条自然语言语句与SPARQL查询映射的模板化数据集。通过GPT-2（124M）、Phi-1.5（1.3B）和GPT-3.5-Turbo的实验发现：尽管所有模型在熟悉模式上表现良好，但仅GPT-3.5-Turbo展现出有意义的泛化能力，表明模型规模与多样化预训练对领域适应性至关重要。然而，在实现稳健泛化、处理多样语言数据及开发可扩展解决方案方面仍面临显著挑战。
原文摘要 · Abstract (English)
Knowledge graphs offer an excellent solution for representing the lexical-semantic structures of lexicographic data. However, working with the SPARQL query language represents a considerable hurdle for many non-expert users who could benefit from the advantages of this technology. This paper addresses the challenge of creating natural language interfaces for lexicographic data retrieval on knowledge graphs such as Wikidata. We develop a multidimensional taxonomy capturing the complexity of Wikidata's lexicographic data ontology module through four dimensions and create a template-based dataset with over 1.2 million mappings from natural language utterances to SPARQL queries. Our experiments with GPT-2 (124M), Phi-1.5 (1.3B), and GPT-3.5-Turbo reveal significant differences in model capabilities. While all models perform well on familiar patterns, only GPT-3.5-Turbo demonstrates meaningful generalization capabilities, suggesting that model size and diverse pre-training are crucial for adaptability in this domain. However, significant challenges remain in achieving robust generalization, handling diverse linguistic data, and developing scalable solutions that can accommodate the full complexity of lexicographic knowledge representation.
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。