Evaluation of Chunking Strategies for Effective Text Embedding in Low-Resource Language on Agricultural Documents

TL;DR

This study compares four text chunking strategies for improving text embedding and retrieval in Khmer agricultural documents within a RAG framework, highlighting the effectiveness of recursive chunking.

Contribution

It introduces a systematic evaluation of chunking methods for low-resource languages, demonstrating the superiority of recursive chunking in this context.

Findings

Recursive chunking achieved the lowest L2 distance and highest relevance scores.

Statistically significant improvement over sentence-based chunking in L2 distance.

Character-based recursive chunking outperforms other methods in retrieval metrics.

Abstract

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.