Document Type : Original/Review Paper
Authors
Faculty of Computer Engineering, K. N. Toosi University of Technology, Tehran, Iran
10.22044/jadm.2025.16583.2785
Abstract
Dialogue understanding for low-resource languages like Persian remains challenging due to limited annotated data, which constrains supervised training at scale. We propose a simple yet effective training-free method that combines machine translation, retrieval-based example selection, and prompting with a large language model (GPT-4o) to improve zero-shot cross-lingual performance. Given a Persian utterance translated into English, our method retrieves semantically and lexically similar English examples using a hybrid similarity function, translates them back into Persian, and constructs a few-shot prompt tailored to the input. This input-sensitive strategy enhances the quality of the examples, helping the model align more effectively with each instance. Experimental results on the Persian-ATIS dataset show that our approach improves intent detection and achieves competitive slot filling performance, outperforming state-of-the-art baselines without requiring any supervision in the target language. The modular pipeline is easy to reproduce and, in future work, can be extended to other low-resource languages, tasks, or retrieval configurations. The repository of our work is available at https://anonymous.4open.science/r/Persian_Language_Understanding-FDF4.
Keywords
- Cross-lingual Adaptation
- Natural Language Understanding
- Persian Language
- Large Language Models
- ChatGPT
Main Subjects
[1] Y. Wang, J. Zhang, T. Shi, D. Deng, Y. Tian, and T. Matsumoto, "Recent advances in interactive machine translation with large language models," IEEE Access, vol. 12, pp. 179353-179382, 2024.
[2] H. Zhang, P. S. Yu, and J. Zhang, "A systematic survey of text summarization: From statistical methods to large language models," ACM Computing Surveys, vol. 57, no. 11, pp. 1-41, 2025.
[3] A. Algherairy and M. Ahmed, "Prompting large language models for user simulation in task-oriented dialogue systems," Computer Speech & Language, vol. 89, no. 101697, 2025.
[4] V. Pratap, A. Tjandra, B. Shi, P. Tomasello, A. Babu, S. Kundu, A. Elkahky, Z. Ni, A. Vyas, and M. Fazel-Zarandi, "Scaling speech technology to 1,000+ languages," Journal of Machine Learning Research, vol. 25, no. 97, pp. 1-52, 2024.
[5] P. Pakray, A. Gelbukh, and S. Bandyopadhyay, "Natural language processing applications for low-resource languages," Natural Language Processing, vol. 31, no. 2, pp. 183-197, 2025.
[6] M. Firdaus, H. Golchha, A. Ekbal, and P. Bhattacharyya, "A deep multi-task model for dialogue act classification, intent detection and slot filling," Cognitive Computation, vol. 13, no. 3, pp. 626-645, 2021.
[7] A. Algherairy and M. Ahmed, "A review of dialogue systems: current trends and future directions," Neural Computing and Applications, vol. 36, no. 12, pp. 6325-6351, 2024.
[8] Z. Zhang, R. Takanobu, Q. Zhu, M. Huang, and X. Zhu, "Recent advances and challenges in task-oriented dialog systems," Science China Technological Sciences, vol. 63, no. 10, pp. 2011-2027, 2020.
[9] C.-W. Goo, G. Gao, Y.-K. Hsu, C.-L. Huo, T.-C. Chen, K.-W. Hsu, and Y.-N. Chen, "Slot-gated modeling for joint slot filling and intent prediction," in Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2018, vol. 2 (Short Papers), pp. 753-757.
[10] M. A. Hedderich, L. Lange, H. Adel, J. Strötgen, and D. Klakow, "A survey on recent approaches for natural language processing in low-resource scenarios," arXiv preprint arXiv:2010.12309, 2020.
[11] T. Adimulam, S. Chinta, and S. K. Pattanayak, "Transfer learning in natural language processing: Overcoming low-resource challenges," International Journal of Enhanced Research in Science Technology & Engineering, vol. 11, no.12, pp. 65-79, 2022.
[12] Y. Fu, N. Lin, B. Chen, Z. Yang, and S. Jiang, "Cross-lingual named entity recognition for heterogenous languages," IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 31, pp. 371-382, 2022.
[13] P. Sahoo, A. K. Singh, S. Saha, V. Jain, S. Mondal, and A. Chadha, "A systematic survey of prompt engineering in large language models: Techniques and applications," arXiv preprint arXiv:2402.07927, 2024.
[14] S. Tahery and S. Farzi, "An Adapted Few-Shot Prompting Technique Using ChatGPT to Advance Low-Resource Languages Understanding," IEEE Access, vol. 13, pp. 93614-93628, 2025.
[15] P. Lewis, E. Perez, A. Piktus, F. Petroni, V. Karpukhin, N. Goyal, H. Küttler, M. Lewis, W.-t. Yih, and T. Rocktäschel, "Retrieval-augmented generation for knowledge-intensive nlp tasks," Advances in neural information processing systems 33, Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, pp. 9459-9474.
[16] A. Conneau and G. Lample, "Cross-lingual language model pretraining," Advances in neural information processing systems 32, Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, pp. 7057–7067.
[17] A. Siddhant, M. Johnson, H. Tsai, N. Ari, J. Riesa, A. Bapna, O. Firat, and K. Raman, "Evaluating the cross-lingual effectiveness of massively multilingual neural machine translation," in Proceedings of the AAAI conference on artificial intelligence, 2020, vol. 34, no. 05, pp. 8854-8861.
[18] C. D. Manning, P. Raghavan, and H. Schütze, An introduction to information retrieval, Cambridge University Press, 2009.
[19] M. J. Sabet, P. Dufter, F. Yvon, and H. Schütze, "SimAlign: High quality word alignments without parallel training data using static and contextualized embeddings," in Findings of the Association for Computational Linguistics: EMNLP 2020, 2020: Association for Computational Linguistics, pp. 1627-1643.
[20] M. Akbari, A. H. Karimi, T. Saeedi, Z. Saeidi, K. Ghezelbash, F. Shamsezat, M. Akbari, and A. Mohades, "A persian benchmark for joint intent detection and slot filling," arXiv preprint arXiv:2303.00408, 2023.
[21] E. Razumovskaia, G. Glavaš, O. Majewska, A. Korhonen, and I. Vulić, "Crossing the Conversational Chasm: A Primer on Multilingual Task-Oriented Dialogue Systems," Journal of Artificial Intelligence Research, vol. 24, pp. 351-1402, 2022.
[22] K. Yu, H. Li, and B. Oguz, "Multilingual seq2seq training with similarity loss for cross-lingual document classification," in Proceedings of the third workshop on representation learning for NLP, 2018, pp. 175-179.
[23] B. McCann, J. Bradbury, C. Xiong, and R. Socher, "Learned in translation: Contextualized word vectors," Advances in neural information processing systems 30, Annual Conference on Neural Information Processing Systems 2017, NeurIPS 2017, pp. 6294-6305.
[24] S. Schuster, S. Gupta, R. Shah, and M. Lewis, "Cross-lingual transfer learning for multilingual task oriented dialog," in Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2019, pp. 3795–3805.
[25] T. Pires, E. Schlinger, and D. Garrette, "How multilingual is multilingual BERT?," in Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019: Association for Computational Linguistics, pp. 4996–5001.
[26] A. Conneau, K. Khandelwal, N. Goyal, V. Chaudhary, G. Wenzek, F. Guzmán, E. Grave, M. Ott, L. Zettlemoyer, and V. Stoyanov, "Unsupervised cross-lingual representation learning at scale," in Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2019: Association for Computational Linguistics, pp. 8440–8451.
[27] R. Zadkamali, S. Momtazi, and H. Zeinali, "Intent detection and slot filling for Persian: Cross-lingual training for low-resource languages," Natural Language Processing, vol. 31, no. 2, pp. 559-574, 2025.
[28] Z. Li, C. Hu, J. Chen, Z. Chen, X. Guo, and R. Zhang, "Improving Zero-Shot Cross-Lingual Transfer via Progressive Code-Switching," in Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence (IJCAI-24), 2024, pp. 6388-6396.
[29] L. Qin, Q. Chen, T. Xie, Q. Li, J.-G. Lou, W. Che, and M.-Y. Kan, "GL-CLeF: A global-local contrastive learning framework for cross-lingual spoken language understanding," in Proceedings of the 60th annual meeting of the association for computational linguistics, vol. 1 (Long Papers), 2022, pp. 2677–2686.
[30] L. Qin, M. Ni, Y. Zhang, and W. Che, "Cosda-ml: Multi-lingual code-switching data augmentation for zero-shot cross-lingual nlp," in Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI-20), 2020, pp. 3853–3860.
[31] Z. Liu, G. I. Winata, Z. Lin, P. Xu, and P. Fung, "Attention-informed mixed-language training for zero-shot cross-lingual task-oriented dialogue systems," in Proceedings of the AAAI Conference on Artificial Intelligence, 2020, vol. 34, no. 05, pp. 8433-8440.
[32] P. Safari and M. Shamsfard, "Data augmentation and preparation process of PerInfEx: a Persian chatbot with the ability of information extraction," IEEE Access, vol. 12, pp. 19158-19180, 2024.
[33] S. Tahery, S. Kianian, and S. Farzi, "Cross-Lingual NLU: Mitigating Language-Specific Impact in Embeddings Leveraging Adversarial Learning," in Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), 2024, pp. 4158-4163.
[34] W. U. Ahmad, Z. Zhang, X. Ma, K.-W. Chang, and N. Peng, "Cross-lingual dependency parsing with unlabeled auxiliary languages," in Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL), 2019, pp. 372-382.
[35] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, "Generative adversarial nets," Advances in neural information processing systems 27, Annual Conference on Neural Information Processing Systems 2014, NeurIPS 2014, pp. 2672-2680.
[36] S. Tahery and S. Farzi, "An Invasive Embedding Model in Favor of Low-Resource Languages Understanding," ACM Transactions on Asian and Low-Resource Language Information Processing, vol. 24, no. 12, pp. 1-24, 2025.
[37] J. Pei, G. Yan, M. De Rijke, and P. Ren, "Mixture-of-Languages Routing for Multilingual Dialogues," ACM Transactions on Information Systems, vol. 42, no. 6, pp. 1-33, 2024.
[38] T. Labruna, S. Brenna, and B. Magnini, "Dynamic Task-Oriented Dialogue: A Comparative Study of Llama-2 and Bert in Slot Value Generation," in Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop, 2024, pp. 358-368.
[39] A. R. Ghasemi and J. Salimi Sartakhti, "Multilingual Language Models in Persian NLP Tasks: A Performance Comparison of Fine-Tuning Techniques," Journal of AI and Data Mining, vol. 13, no. 1, pp. 107-117, 2025.
[40] W. Pan, Q. Chen, X. Xu, W. Che, and L. Qin, "A preliminary evaluation of chatgpt for zero-shot dialogue understanding," arXiv preprint arXiv:2304.04256, 2023.
[41] Z. Zhu, X. Cheng, H. An, Z. Wang, D. Chen, and Z. Huang, "Zero-shot spoken language understanding via large language models: A preliminary study," in Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), 2024, pp. 17877-17883.
[42] Z. Borhanifard, H. Basafa, S. Z. Razavi, and H. Faili, "Persian language understanding in task-oriented dialogue system for online shopping," in 2020 11th International Conference on Information and Knowledge Technology (IKT), 2020: IEEE, pp. 79-84.
[43] M. Akbari, A. Mohades, and M. H. Shirali-Shahreza, "A hybrid architecture for out of domain intent detection and intent discovery," in 2025 11th International Conference on Web Research (ICWR), 2025: IEEE, pp. 137-144.
[44] E. A. Abyaneh, R. Zolfaghari, and A. A. Abyaneh, "User Intent Detection in Persian Text-Based Chatbots: A Comprehensive Review of Methods and Challenges," in 2025 11th International Conference on Web Research (ICWR), 2025: IEEE, pp. 243-249.
[45] A. Singhal, "Modern information retrieval: A brief overview," IEEE Data Eng. Bull., vol. 24, no. 4, pp. 35-43, 2001.
[46] D. Kamali, B. Janfada, M. E. Shenasa, and B. Minaei-Bidgoli, "Evaluating Persian Tokenizers," arXiv preprint arXiv:2202.10879, 2022.
)