arXiv subjects

Nimol Thuon

Publications and source records attributed to Nimol Thuon.

6 recordsLinked to original sources

arXiv2026

Do MLLMs Really Understand Low-Resource Khmer Documents? A Pilot Study on Khmer Document VQA

Recent multimodal large language models (MLLMs) have advanced document understanding, visual question answering, and text extraction. However, their reliability in low-resource, non-Latin settings remains uncertain. Khmer form documents present particular challenges because they contain complex script forms, mixed Khmer-English fields, and monetary values in both Cambodian Riel and US Dollars. Available resources for Khmer Document VQA are also limited. This paper presents a pilot diagnostic evaluation of open MLLMs on Khmer document images. We construct an evaluation subset from the previously introduced KH-FUNSD collection, covering invoices, receipts, quotations, and other business forms. The subset includes questions in English and Khmer, with answers retained in their original English, Khmer, mixed-script, or numeric forms. Rather than introducing a full public benchmark, this study examines the capabilities and failure modes of existing models. We evaluate representative open Qwen-VL models using direct image-based prompting and compare parser-assisted and external OCR-assisted configurations with Qwen3-VL-8B. Direct Qwen3-VL-8B outperforms smaller models, achieving 51.9% overall accuracy, although performance remains limited for Khmer-script and mixed-script answers. External OCR produces the strongest results, reaching 61.9% with Tesseract and 61.6% with PaddleOCR. Nevertheless, Khmer-script answers remain substantially more difficult than English and numeric fields. The results indicate that current MLLMs can process visually clear English and structured numeric content, but reliable native Khmer document understanding remains an open challenge.

cs.CL↗

arXiv2026

KSE-Web: An Analysis of Hybrid Retrieval and LLM-Assisted Query Expansion for Low-Resource Khmer Semantic Search

As a low-resource language, Khmer presents several retrieval challenges, including limited annotated data, ambiguous word boundaries, weak support in multilingual embedding models, and frequent mixed Khmer-English usage. This paper presents KSE-Web, an analysis of hybrid retrieval and LLM-assisted query expansion for Khmer semantic search. We construct the dataset from approximately 17K candidate Khmer titles and retain 3K cleaned full-text Khmer documents after filtering, normalization, deduplication, and document-length control. The dataset includes 300 manually reviewed user-style Khmer search queries and silver relevance labels with partial human verification. We evaluate character n-gram BM25, multilingual dense retrieval, hybrid BM25+dense retrieval, and LLM-assisted query expansion using Qwen2.5 models. Experimental results show that BM25 achieves the strongest overall performance, reaching 0.943 Recall and 0.876 nDCG. Hybrid BM25+dense retrieval performs comparably, achieving 0.929 Recall and 0.871 nDCG, while dense retrieval alone performs lower. LLM-assisted query expansion does not outperform non-expanded retrieval; however, Qwen2.5-3B produces substantially stronger expanded-query results than Qwen2.5-0.5B, suggesting that LLM size and expansion quality matter for low-resource Khmer retrieval. Our analysis further shows that direct LLM expansion can introduce topic drift, generic terms, and noisy reformulations, while simple filtering may remove useful semantic cues. These findings highlight both the potential and limitations of LLM-assisted retrieval for Khmer semantic search and provide a foundation for future Khmer retrieval datasets with stronger human-verified annotations and Khmer-aware retrieval models. The dataset and documentation will be made available at github.com/back-kh/KhmerSemantic-Search.

cs.CL↗

arXiv2025

KH-FUNSD: A Hierarchical and Fine-Grained Layout Analysis Dataset for Low-Resource Khmer Business Document

Automated document layout analysis remains a major challenge for low-resource, non-Latin scripts. Khmer is a language spoken daily by over 17 million people in Cambodia, receiving little attention in the development of document AI tools. The lack of dedicated resources is particularly acute for business documents, which are critical for both public administration and private enterprise. To address this gap, we present \textbf{KH-FUNSD}, the first publicly available, hierarchically annotated dataset for Khmer form document understanding, including receipts, invoices, and quotations. Our annotation framework features a three-level design: (1) region detection that divides each document into core zones such as header, form field, and footer; (2) FUNSD-style annotation that distinguishes questions, answers, headers, and other key entities, together with their relationships; and (3) fine-grained classification that assigns specific semantic roles, such as field labels, values, headers, footers, and symbols. This multi-level approach supports both comprehensive layout analysis and precise information extraction. We benchmark several leading models, providing the first set of baseline results for Khmer business documents, and discuss the distinct challenges posed by non-Latin, low-resource scripts. The KH-FUNSD dataset and documentation will be available at URL.

cs.CL↗

arXiv2024

Khmer Semantic Search Engine (KSE): Digital Information Access and Document Retrieval

The search engine process is crucial for document content retrieval. For Khmer documents, an effective tool is needed to extract essential keywords and facilitate accurate searches. Despite the daily generation of significant Khmer content, Cambodians struggle to find necessary documents due to the lack of an effective semantic searching tool. Even Google does not deliver high accuracy for Khmer content. Semantic search engines improve search results by employing advanced algorithms to understand various content types. With the rise in Khmer digital content such as reports, articles, and social media feedback enhanced search capabilities are essential. This research proposes the first Khmer Semantic Search Engine (KSE), designed to enhance traditional Khmer search methods. Utilizing semantic matching techniques and formally annotated semantic content, our tool extracts meaningful keywords from user queries, performs precise matching, and provides the best matching offline documents and online URLs. We propose three semantic search frameworks: semantic search based on a keyword dictionary, semantic search based on ontology, and semantic search based on ranking. Additionally, we developed tools for data preparation, including document addition and manual keyword extraction. To evaluate performance, we created a ground truth dataset and addressed issues related to searching and semantic search. Our findings demonstrate that understanding search term semantics can lead to significantly more accurate results.

cs.IR↗

arXiv2024

KSW: Khmer Stop Word based Dictionary for Keyword Extraction

This paper introduces KSW, a Khmer-specific approach to keyword extraction that leverages a specialized stop word dictionary. Due to the limited availability of natural language processing resources for the Khmer language, effective keyword extraction has been a significant challenge. KSW addresses this by developing a tailored stop word dictionary and implementing a preprocessing methodology to remove stop words, thereby enhancing the extraction of meaningful keywords. Our experiments demonstrate that KSW achieves substantial improvements in accuracy and relevance compared to previous methods, highlighting its potential to advance Khmer text processing and information retrieval. The KSW resources, including the stop word dictionary, are available at the following GitHub repository: (https://github.com/back-kh/KSWv2-Khmer-Stop-Word-based-Dictionary-for-Keyword-Extraction.git).

cs.IR↗

arXiv2024

Development of an open education resources (OER) system: a comparative analysis and implementation approach

Several institutions are collaborating on the development of a new web-based Open Education Resources (OER) system designed exclusively for non-commercial educational purposes. This initiative is underpinned by meticulous research aimed at constructing an OER system that optimizes user experiences across diverse user profiles. A significant emphasis is placed on utilizing open-source tools, frameworks, and technologies. The project includes a comparative analysis of the top five open-source Learning Management Systems (LMS), providing critical insights to inform the development process. The primary objective is to create a web-based system that facilitates the sharing of educational resources for non-commercial users, leveraging information and communication technologies. The project is structured around two key teams: a research team and a development team. This comprehensive approach is intended to establish a robust, user-centric OER system, informed by insights from existing platforms and the latest advancements in open education resource development.

cs.CY↗