针对高棉语农业文本，优化分块策略提升低资源语言检索效果
Evaluation of Chunking Strategies for Effective Text Embedding in Low-Resource Language on Agricultural Documents
- 采用字符级递归分块，300字符为单位，兼顾语言结构与信息完整性
- 最优方案在距离、相关性、覆盖率上均领先，尤其IoU达0.6441
- 适合低资源复杂形态语言的文本检索任务，如农业文献智能问答
本研究在检索增强生成框架下，对比四种文本分块方法（递归式、高棉语感知式、基于句子、基于大模型）在高棉语农业文档中的表现。使用BGE-M3多语言嵌入模型编码文档块，通过FAISS进行检索，基于18个问答对进行五折交叉验证，采用平均检索得分（L2距离）、答案相关性、高棉语覆盖率和高棉语交并比四项指标评估。结果表明，以300字符为单位的字符级递归分块表现最佳，L2距离最低（0.4295 ± 0.0461），答案相关性最高（0.8663 ± 0.0199），高棉语交并比达0.6441。配对t检验显示，该方法在L2距离上显著优于基于句子的分块（p = 0.0121）。研究强调了分块粒度与结构保留对复杂低资源语言密集检索的重要性。
原文摘要 · Abstract (English)
In this study, we compare the performance of four text chunking approaches: Recursive, Khmer-Aware, Sentence-Based, and LLM-Based within a Retrieval-Augmented Generation (RAG) framework applied to Khmer agricultural documents. The document chunks are encoded using the BGE-M3 multilingual embedding model and retrieved using the FAISS library. Performance is evaluated using four metrics: Average Retrieval Score (L2 distance), Answer Relevance, Khmer Coverage, and Khmer Intersection over Union, all measured against ground-truth question-answer pairs. For evaluation, we perform 5-fold cross-validation over 18 question-answer pairs. We observe the best performance for the character-based Recursive chunking method with a chunk size of 300 characters, achieving the lowest L2 distance (0.4295 +- 0.0461), highest Answer Relevance (0.8663 +- 0.0199), and highest Khmer IoU (0.6441 +- 0.0347). A paired t-test shows a statistically significant improvement over the Sentence-Based chunking method in L2 distance (p = 0.0121). These results highlight the importance of segmentation granularity and structural preservation for optimizing dense retrieval in morphologically complex, low-resource languages such as Khmer.
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。