The classical text preprocessing pipeline, comprising Tokenisation, Normalisation, Stop Words Removal, and Stemming/Lemmatisation, has been implemented in many systems for ontology matching (OM). However, the lack of standardisation in text preprocessing creates diversity in the mapping results. In this paper, we investigate the effect of the text preprocessing pipeline on 8 Ontology Alignment Evaluation Initiative (OAEI) tracks with 49 distinct alignments. We find that Tokenisation and Normalisation (categorised as Phase 1 text preprocessing) are more effective than Stop Words Removal and Stemming/Lemmatisation (categorised as Phase 2 text preprocessing). We propose two novel approaches to repair unwanted false mappings that occur in Phase 2 text preprocessing. One is a pre hoc logic-based repair approach used before text preprocessing, employing an ontology-specific check to find common words that cause false mappings. The other repair approach is the post hoc large language model (LLM)-based approach, used after text preprocessing, which utilises the strong background knowledge provided by LLMs to repair non-existent and counter-intuitive false mappings. The experimental results indicate that these two approaches can significantly improve the matching correctness and the overall matching performance.

翻译：经典的文本预处理流水线，包括分词、规范化、停用词去除以及词干/词形还原，已被广泛应用于诸多本体匹配系统中。然而，文本预处理缺乏标准化导致了映射结果的多样性。本文针对8个本体对齐评估计划（OAEI）基准测试集中的49个不同对齐任务，系统研究了文本预处理流水线的影响效应。研究发现，分词与规范化（归类为第一阶段文本预处理）的效果优于停用词去除与词干/词形还原（归类为第二阶段文本预处理）。我们提出了两种新颖方法，用于修复第二阶段文本预处理中产生的不良虚假映射：其一是基于逻辑的事前修复方法，在文本预处理之前，通过本体特异性检查识别导致虚假映射的常见词汇；其二是基于大语言模型（LLM）的事后修复方法，在文本预处理之后，利用LLM强大的背景知识修复不存在的反直觉虚假映射。实验结果表明，这两种方法能显著提升匹配正确率及整体匹配性能。