Talk · IEEE/ACM International Conference on Utility and Cloud Computing · December 1, 2025

Enhancing Question Answering for Low-Resource Languages: The Case of Kazakh Language

Arailym Tleubayeva, Zhansaya Makhambetova, Aigerim Mansurova, Adai Shomanov

Abstract

The Kazakh language, with its agglutinative morphology and scarce annotated data, presents challenges for accurate Question Answering (QA). This study proposes a three-stage framework to improve multilingual QA performance in low-resource settings through model adaptation, semantic representation evaluation, and retrieval optimization. First, multilingual QA models (mT5, XLM-R, mDeBERTa-v3, AYA, Kaz-RoBERTa, and KazakhBERTmulti) were fine-tuned using SentencePiece tokenization and adapter-based training. Second, five embedding models were benchmarked via Domain and QuestionType classification, with Snowflake-Arctic achieving the highest accuracy (0.87) and BGE-M3 demonstrating strong robustness. Finally, a memory-aware retrieval mechanism was implemented by integrating Safe Memory clustering with FAISS indexing, improving contextual recall (R@10 = 0.984) without loss of precision. Results show that adapted multilingual transformers consistently outperform native Kazakh models, while enhanced retrieval strengthens grounding and cross-domain robustness. The framework provides a reproducible pathway toward scalable and linguistically inclusive QA systems for low-resource languages.

Topic ModelingNatural Language Processing TechniquesInformation Retrieval and Search Behaviorquestion answeringlow-resource languagesKazakh language

Enhancing Question Answering for Low-Resource Languages: The Case of Kazakh Language

Abstract

More by Adai Shomanov