Saksonita Khoeurn

A Semantic-Layer-Mediated Agent for Natural Language to SQL over Heterogeneous Enterprise Databases

Ha Jeong Kim, Saksonita Khoeurn, Ye Ji Yoon

Natural language-to-SQL (NL2SQL) over real-world enterprise databases remains significantly more challenging than on academic benchmarks. Enterprise schemas often contain hundreds of physical tables with cryptic column names, heterogeneous SQL dialects, and complex analytical workloads requiring nested aggregations, temporal reasoning, and multi-table joins. …

A Semantic-Layer-Mediated Agent for Natural Language to SQL over Heterogeneous Enterprise Databases

Ha Jeong Kim, Saksonita Khoeurn, Ye Ji Yoon

Natural language-to-SQL (NL2SQL) over real-world enterprise databases remains significantly more challenging than on academic benchmarks. Enterprise schemas often contain hundreds of physical tables with cryptic column names, heterogeneous SQL dialects, and complex analytical workloads requiring nested aggregations, temporal reasoning, and multi-table joins. …

kr (code pays fourni par la source)

Closing the Quality Gap in Low-Resource Text-to-Speech: LoRA Fine-Tuning of VoxCPM2 for Khmer and Korean

Phannet Pov, Sovandara Chhoun, Hyun Woo Park, Wan-Sup Cho et autres

Large pretrained text-to-speech (TTS) models sound almost human for well-resourced languages, but much worse for languages that are rare in their training data. We study this quality gap for Khmer and Korean using VoxCPM2, a 2.4B-parameter, tokenizer-free TTS model that joins a …

Closing the Quality Gap in Low-Resource Text-to-Speech: LoRA Fine-Tuning of VoxCPM2 for Khmer and Korean

Phannet Pov, Sovandara Chhoun, Hyun Woo Park, Wan-Sup Cho et autres

Large pretrained text-to-speech (TTS) models sound almost human for well-resourced languages, but much worse for languages that are rare in their training data. We study this quality gap for Khmer and Korean using VoxCPM2, a 2.4B-parameter, tokenizer-free TTS model that joins a …

kr, kh (code pays fourni par la source)

A Comparative Study of Language Models for Khmer Retrieval-Augmented Question Answering

Sereiwathna Ros, Phannet Pov, Ratanaktepi Chhor, Kimleang Ly et autres

Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm for grounding large language model (LLM) outputs in retrieved evidence, thereby reducing hallucination and improving factual accuracy. Its efficacy, however, remains largely unexamined for low-resource, non-Latin-script languages such as Khmer. In this paper, …

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

Sovandara Chhoun, Pichdara Po, Sereiwathna Ros, Wan-Sup Cho et autres

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 …

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

Sovandara Chhoun, Pichdara Po, Sereiwathna Ros, Wan-Sup Cho et autres

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 …

kr (code pays fourni par la source)

A Comparative Study of Language Models for Khmer Retrieval-Augmented Question Answering

Sereiwathna Ros, Phannet Pov, Ratanaktepi Chhor, Kimleang Ly et autres

Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm for grounding large language model (LLM) outputs in retrieved evidence, thereby reducing hallucination and improving factual accuracy. Its efficacy, however, remains largely unexamined for low-resource, non-Latin-script languages such as Khmer. In this paper, …

kr, kh (code pays fourni par la source)

Reliability assessment of agricultural sensors evaluated through algal coverage in hydroponic tomato production systems

Saksonita Khoeurn, No Hyeon Park, Hye Kyoung Jahng, Jaehyuk Jeon et autres

In modern agricultural systems, hydroponics represents a crucial advancement in integrating digital technologies and precision farming practices for sensor-mediated cultivation. These systems employ continuous environmental monitoring to enhance operational efficiency and promote plant growth. However, environmental factors and technical issues can undermine …

kr (code pays fourni par la source)

Explainable AI and Voting Ensemble Model to Predict the Results of Seafood Product Importation Inspections

Saksonita Khoeurn, Wan-Sup Cho

Background: As the volume of imported food flowing into South Korea rapidly increases due to the expansion of free trade agreements, improving inspection efficiency through artificial intelligence technology emerges as a critical task, particularly as time and cost expenditures for safety inspections …

kr (code pays fourni par la source)

Predicting cucumber shipments using artificial intelligence technology

Eun-Woo Kim, Saksonita Khoeurn, Wan-Sup Cho, P. Kim

기후변화로 인해 농작물 생산과 가격 불확실성이 높아짐에 따라 빅데이터와 AI를 농산물 출하량 예측에 활용하려는 연구가 활발하게 진행되고 있다. 농산물 출하량은 농산물 유통 최적화를 위한 중요한 정보로 활용될 수 있기 때문이다. 농산물 출하량 예측은 가격에 영향을 미칠 뿐 아니라 농가의 출하량과 유통회사의 유통량 …

Explainable AI and Voting Ensemble Model to Predict the Results of Seafood Product Importation Inspections

Saksonita Khoeurn, Wan-Sup Cho

The lack of a generalizable machine learning model for predicting the safety of food for 1 human consumption is a significant challenge for policymakers and responsible authorities. This 2 study provides a step-by-step guide to predict the results of seafood product import …

kr (code pays fourni par la source)