Cross-Lingual Transfer for Semantic Role Labeling in Indonesian
DOI:
https://doi.org/10.5614/itbj.ict.res.appl.2026.20.2.1Keywords:
cross-lingual transfer, multilingual language model, semantic role labeling, low-resource NLP, annotated corpora, CoNLL-2012Abstract
Semantic role labeling is a semantic analysis task that aims to identify the semantic relationships within a sentence, such as who did what to whom, where, when, and so on. Current semantic role labeling (SRL) models for the Indonesian language still face challenges in achieving strong performance due to the limited availability of annotated corpora, especially compared with English SRL models. Therefore, this paper develops an Indonesian SRL model using cross-lingual transfer. This approach addresses the data scarcity problem in Indonesian SRL by leveraging the availability of annotated English-language corpora. The method uses multilingual models and SRL datasets from both English and Indonesian. The multilingual models used in this study are XLM-R and mT5, both in base and large configurations. The datasets include Universal PropBank Indonesia and Gojali?s dataset for Indonesian, and CoNLL-2012 for English. Evaluation was conducted using test data from Universal PropBank Indonesia and Gojali?s dataset. Among all developed models, XLM-R large with cross-lingual transfer achieved the best performance, with an F1 score of 0.916 on Gojali?s dataset and 0.858 on the combined Universal PropBank Indonesia and Gojali datasets.
Downloads
References
Villodre, L.M., Carreras, X., Litkowski, K.C. & Stevenson, S., Semantic Role Labeling, An introduction. Computational Linguistics, 34, pp.145-159, 2008.
Jurafsky, D. & Martin, J.H., Speech and Language Processing (3rd ed., draft), 2003.
Niklaus, C., Cetto, M., Freitas, A. & Handschuh, S., A Survey on Open Information Extraction, In Proceedings of COLING, pp. 3866-3878, 2018.
Zhang, Z., Wu, Y., Hai, Z., Li, Z., Zhang, S., Zhou, X. & Zhou, X., Semantics-aware BERT for Language Understanding, In Proceedings of AAAI, 2019.
Gunawan, Y.H.B. & Khodra, M.L., Multi-document Summarization using Semantic Role Labeling, In Proceedings of ICAICTA pp. 1-6, 2020. doi: 10.1109/ICAICTA49861.2020.9429055.
Gojali, F., Span-based Semantic Role Labeling for Indonesian News Summarization (Unpublished Undergraduate Thesis), Institut Teknologi Bandung, 2022.
Li, Z., He, S., Zhao, H., Zhang, Y., Zhang, Z., Zhou, X. & Zhou, X., End-to-end Semantic Role Labeling, In Proceedings of AAAI, pp. 6730-6737, 2019. doi:10.1609/aaai.v33i01.33016730.
Pradhan, S., Moschitti, A., Xue, N., Uryupina, O. & Zhang, Y., CoNLL-2012 Shared Task, Modeling Multilingual Coreference, in Proceedings of CoNLL. pp. 1-40, 2012.
Li, T., Jawale, P.A., Palmer, M. & Srikumar, V., Structured Tuning for Semantic Role Labeling, In Proceedings of ACL, pp. 8402-8412. 2020.
Oliveira, S., Loureiro, D., & Jorge, A., Improving Portuguese SRL with Transformers, In Proceedings of DSAA, 2021. doi:10.1109/DSAA53316.2021.9564238 .
Devlin, J., Chang, M.W., Lee, K. & Toutanova, K., BERT: Pre-training of Deep Bidirectional Transformers, in Proceedings of NAACL-HLT, 2019.
Conneau, A., Khandelwal, K., Goyal, N., Chaudhary, V., Wenzek, G., Guzm, F., Grave, E., Ott, M., Zettlemoyer, L. & Stoyanov, V., Cross-lingual Representation Learning at Scale, in Proceedings of ACL, pp. 8440-8451, 2020.
Xue, L., Constant, N., Roberts, A., Kale, M., Al-Rfou, R., Siddhant, A., Barua, A. & Raffel, C., mT5: A Multilingual Text-to-text Transformer, in Proceedings of NAACL-HLT, pp. 483-498, 2021.
Jindal, I., Rademaker, A., Ulewicz, M., Linh, H., Nguyen, H., Tran, K.N., Zhu, H. & Li, Y., Universal Proposition Bank 2.0, in Proceedings of LREC, pp. 1700-1711, 2022.
Shi, P. & Lin, J.J., Simple BERT Models for SRL, arXiv preprint arXiv,1904,05255, 2019.
Wilie, B., Vincentio, K., Winata, G.I., Cahyawijaya, S., Li, X., Lim, Z.Y., Soleman, S., Mahendra, R., Fung, P., Bahar, S. & Purwarianti, A., IndoNLU: Benchmark for Indonesian NLP, in Proceedings of AACL-IJCNLP, pp. 843-857, 2020.
