A Comprehensive Survey of Semantic Role Labeling
Keywords:
Semantic Role Labeling, Natural Language Processing, Natural Language Understanding, Predicate-Argument Structure, Neural NetworksAbstract
Semantic Role Labeling (SRL) is a core Natural Language Processing (NLP) task focused on identifying predicate-argument structures and assigning semantic labels like agent or goal, which is crucial for natural language understanding (NLU) in applications such as question answering and information extraction. The field has evolved from early reliance on syntactic information to advanced neural network architectures, including Transformer models and pre-trained language models (PLMs). Key approaches include span-based and dependency-based SRL, with a growing trend towards incorporating higher-order graph structures for richer interactions. A novel paradigm, Definition-based SRL (DSRL), redefines the task as natural language generation, where models explain semantic relationships in human-readable definitions. Despite progress, challenges persist in handling nominal and non-verbal predicates, cross-lingual and low-resource scenarios due to data scarcity, and annotation inconsistencies. Future work aims for end-to-end and document-level SRL, integrating broader contextual information. Large Language Models (LLMs) are significantly transforming SRL by enabling data generation and serving as core architectural components for tasks like DSRL, promising enhanced semantic understanding and zero-shot capabilities. However, challenges remain regarding computational cost and potential for erroneous outputs.
References
D. Gildea and D. Jurafsky, "Automatic labeling of semantic roles," Computational linguistics, vol. 28, no. 3, pp. 245-288, 2002.
H. Chen et al., "Semantic Role Labeling: A Systematical Survey," arXiv preprint arXiv:2502.08660, 2025.
S. Conia, R. Orlando, F. Brignone, F. Cecconi, and R. Navigli, "InVeRo-XL: Making cross-lingual Semantic Role Labeling accessible with intelligible verbs and roles," in Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, 2021: Association for Computational Linguistics, pp. 319-328.
S. Kurita, H. Ouchi, K. Inui, and S. Sekine, "Iterative Span Selection: Self-Emergence of Resolving Orders in Semantic Role Labeling," in Proceedings of the 29th International Conference on Computational Linguistics, 2022, pp. 5383-5397.
T. Shi, I. Malioutov, and O. Irsoy, "Semantic role labeling as syntactic dependency parsing," arXiv preprint arXiv:2010.11170, 2020.
J. Kasai, D. Friedman, R. Frank, D. Radev, and O. Rambow, "Syntax-aware neural semantic role labeling with supertags," arXiv preprint arXiv:1903.05260, 2019.
J. Chen, X. He, and Y. Miyao, "Modeling syntactic-semantic dependency correlations in semantic role labeling using mixture models," in Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022, pp. 7959-7969.
N. Wang et al., "An mrc framework for semantic role labeling," arXiv preprint arXiv:2109.06660, 2021.
H. Wu, H. Tan, K. Xu, S. Liu, L. Wu, and L. Song, "Zero-shot cross-lingual conversational semantic role labeling," arXiv preprint arXiv:2204.04914, 2022.
L. Zhang, I. Jindal, and Y. Li, "Label definitions improve semantic role labeling," in Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2022, pp. 5613-5620.
Z. Zhang, E. Strubell, and E. Hovy, "Transfer learning from semantic role labeling to event argument extraction with template-based slot querying," in Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022, pp. 2627-2647.
M. Zhang, P. Liang, and G. Fu, "Enhancing opinion role labeling with semantic-aware word representations from semantic role labeling," in Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), 2019, pp. 641-646.
J. Zou et al., "Semantic role labeling guided out-of-distribution detection," arXiv preprint arXiv:2305.18026, 2023.
E. Spaulding, G. Kazantsev, and M. Dredze, "Joint end-to-end semantic proto-role labeling," in Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 2023, pp. 723-736.
R. Devianti and Y. Miyao, "Transferability of Syntax-Aware Graph Neural Networks in Zero-Shot Cross-Lingual Semantic Role Labeling," in Findings of the Association for Computational Linguistics: EMNLP 2024, 2024, pp. 20-42.
T. Li, G. Kazeminejad, S. W. Brown, M. Palmer, and V. Srikumar, "Learning semantic role labeling from compatible label sequences," arXiv preprint arXiv:2305.14600, 2023.
C. Guan, Y. Cheng, and H. Zhao, "Semantic role labeling with associated memory network," arXiv preprint arXiv:1908.02367, 2019.
S. Conia, A. Bacciu, and R. Navigli, "Unifying cross-lingual semantic role labeling with heterogeneous linguistic resources," in Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2021, pp. 338-351.
S. Conia, E. Barba, A. Scirè, and R. Navigli, "Semantic role labeling meets definition modeling: Using natural language to describe predicate-argument structures," arXiv preprint arXiv:2212.01094, 2022.
C. Zheng and P. Kordjamshidi, "SRLGRN: Semantic role labeling graph reasoning network," arXiv preprint arXiv:2010.03604, 2020.
S. Zhou, Q. Xia, Z. Li, Y. Zhang, Y. Hong, and M. Zhang, "Fast and accurate end-to-end span-based semantic role labeling as word-based graph parsing," arXiv preprint arXiv:2112.02970, 2021.
C. Ai and K. Tu, "Frame semantic role labeling using arbitrary-order conditional random fields," in Proceedings of the AAAI Conference on Artificial Intelligence, 2024, vol. 38, no. 16, pp. 17638-17646.
Z. Li, H. Zhao, R. Wang, and K. Parnow, "High-order semantic role labeling," arXiv preprint arXiv:2010.04641, 2020.
D. Dannélls, R. Johansson, and L. Y. Buhr, "Transformer-based Swedish Semantic Role Labeling through Transfer Learning," in Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), 2024, pp. 16762-16769.
R. Orlando, S. Conia, and R. Navigli, "Exploring non-verbal predicates in semantic role labeling: Challenges and opportunities," arXiv preprint arXiv:2307.01870, 2023.
Y. Zhang, Q. Xia, S. Zhou, Y. Jiang, G. Fu, and M. Zhang, "Semantic role labeling as dependency parsing: Exploring latent tree structures inside arguments," arXiv preprint arXiv:2110.06865, 2021.
Y. Chen, K. Lim, and J. Park, "A Linguistically-Informed Annotation Strategy for Korean Semantic Role Labeling," in Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), 2024, pp. 733-738.
R. Navigli, M. Pinto, P. Silvestri, D. Rotondi, S. Ciciliano, and A. Scirè, "NounAtlas: Filling the Gap in Nominal Semantic Role Labeling," in Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024, pp. 16245-16258.
R. Cai and M. Lapata, "Alignment-free cross-lingual semantic role labeling," in Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020, pp. 3883-3894.
C. Campagnano, S. Conia, and R. Navigli, "SRL4E–Semantic Role Labeling for Emotions: A unified evaluation framework," in Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022, pp. 4586-4601.
