PDF (1.5 MB)
Collect
Submit Manuscript
Open Access

EFSP-TE: End-to-End Frame-Semantic Parsing with Table Encoder

School of Modern Logistics, Shanxi Vocational University of Engineering Science and Technology, Jinzhong 030619, China, and also with School of Computer and Information Technology, Shanxi University, Taiyuan 030006, China
School of Computer and Information Technology and Institute of Information Processing, Shanxi University, Taiyuan 030006, China
Institute for Infocomm Research, A*Star 999002, Singapore
Show Author Information

Abstract

Frame-Semantic Parsing (FSP) aims to extract frame-semantic structures from text. The task usually involves three subtasks sequentially: Target Identification (TI), Frame Identification (FI), and Frame Semantic Role Labeling (FSRL). The three subtasks are closely related while most previous studies model them individually, encountering error propagation and running efficiency problems. Recently, an end-to-end graph-based model is proposed to jointly process three subtasks in one model. However, it still encounters three problems: insufficient semantic modeling between targets and arguments, span missing, and lacking knowledge incorporation of FrameNet. To address the mentioned problems, this paper presents an End-to-end FSP model with Table Encoder (EFSP-TE), which models FSP as two semantically dependent region classification problems and extracts frame-semantic structures from sentences in a one-step manner. Specifically, EFSP-TE incorporates lexical unit knowledge into context encoder via saliency embedding, and develops an effective table representation learning method based on Biaffine network and multi-layer ResNet-style-CNNs (Convolutional Neural Networks), which can fully exploit word-to-word interactions and capture the information of various levels of semantic relations between targets and arguments. In addition, it adopts two separate region-based modules to obtain potential targets and arguments, followed by two interactive classification modules to predict the frames and roles for the potential targets and arguments. Experiments on two public benchmarks show that the proposed approach achieves state-of-the-art performance in end-to-end setting.

References

[1]
C. F. Baker, C. J. Fillmore, and J. B. Lowe, The Berkeley FrameNet project, in Proc. 36 th Annu. Meeting of the Association for Computational Linguistics and 17 th Int. Conf. Computational Linguistics, Volume 1, Montreal, Canada, 1998, pp. 86–90.
[2]
C. J. Fillmore and C. F. Baker, Frame semantics for text understanding, in Proc. NAACL 2001, WordNet and Other Lexical Resources Workshop, https://www.researchgate.net/publication/228948602_Frame_semantics_for_text_understanding, 2023.
[3]

C. J. Fillmore, Frames and the semantics of understanding, Quaderni di Semantica, vol. 6, no. 2, pp. 222–254, 1985.

[4]
C. Baker, M. Ellsworth, and K. Erk, SemEval-2007 task 19: Frame semantic structure extraction, in Proc. Fourth Int. Workshop on Semantic Evaluations (SemEval-2007 ), Prague, Czech Republic, 2007, pp. 99–104.
[5]

D. Das, D. Chen, A. F. T. Martins, N. Schneider, and N. A. Smith, Frame-semantic parsing, Comput. Linguist., vol. 40, no. 1, pp. 9–56, 2014.

[6]
K. M. Hermann, D. Das, J. Weston, and K. Ganchev, Semantic frame identification with distributed word representations, in Proc. 52 nd Annu. Meeting of the Association for Computational Linguistics (Volume 1 : Long Papers ), Baltimore, MD, USA, 2014, pp. 1448–1458.
[7]
S. Liu, Y. Chen, S. He, K. Liu, and J. Zhao, Leveraging FrameNet to improve automatic event detection, in Proc. 54 th Annu. Meeting of the Association for Computational Linguistics (Volume 1 : Long Papers ), Berlin, Germany, 2016, pp. 2134–2143.
[8]
X. Wang, Y. Chen, N. Ding, H. Peng, Z. Wang, Y. Lin, X. Han, L. Hou, J. Li, Z. Liu, et al., MAVEN-ERE: A unified large-scale dataset for event coreference, temporal, causal, and subevent relation extraction, in Proc. 2022 Conf. Empirical Methods in Natural Language Processing, Abu Dhabi, United Arab Emirates, 2022, pp. 926–941.
[9]
S. Guo, R. Li, H. Tan, X. Li, Y. Guan, H. Zhao, and Y. Zhang, A frame-based sentence representation for machine reading comprehension, in Proc. 58 th Annu. Meeting of the Association for Computational Linguistics, Virtual Event, 2020, pp. 891–896.
[10]
S. Guo, Y. Guan, R. Li, X. Li, and H. Tan, Incorporating syntax and frame semantics in neural network for machine reading comprehension, in Proc. 28 th Int. Conf. Computational Linguistics, Barcelona, Spain, 2020, pp. 2635–2641.
[11]

H. Zhao, R. Li, X. Li, and H. Tan, CFSRE: Context-aware based on frame-semantics for distantly supervised relation extraction, Knowl. -Based Syst., vol. 210, p. 106480, 2020.

[12]

Y. Guan, S. Guo, R. Li, X. Li, and H. Zhang, Frame semantics guided network for abstractive sentence summarization, Knowl. -Based Syst., vol. 221, p. 106973, 2021.

[13]
Y. Guan, S. Guo, R. Li, X. Li, and H. Zhang, Integrating semantic scenario and word relations for abstractive sentence summarization, in Proc. 2021 Conf. Empirical Methods in Natural Language Processing, Punta Cana, Dominican Republic, 2021, pp. 2522–2529.
[14]
Y. Guan, S. Guo, R. Li, X. Li, and H. Tan, Frame semantic-enhanced sentence modeling for sentence-level extractive text summarization, in Proc. 2021 Conf. Empirical Methods in Natural Language Processing, Punta Cana, Dominican Republic, 2021, pp. 4045–4052.
[15]
H. Peng, S. Thomson, S. Swayamdipta, and N. A. Smith, Learning joint semantic parsers from disjoint data, in Proc. 2018 Conf. North American Chapter of the Association for Computational Linguistics : Human Language Technologies, Volume 1 (Long Papers ), New Orleans, LA, USA, 2018, pp. 1492–1502.
[16]
X. Chen, C. Zheng, and B. Chang, Joint multi-decoder framework with hierarchical pointer network for frame semantic parsing, in Proc. Findings of the Association for Computational Linguistics : ACL-IJCNLP 2021, Virtual Event, 2021, pp. 2570–2578.
[17]

X. Su, R. Li, X. Li, B. Chang, Z. Hu, X. Han, and Z. Yan, A span-based target-aware relation model for frame-semantic parsing, ACM Transactions on Asian and Low-Resource Language Information Processing, vol. 22, no. 3, p. 90, 2022.

[18]
C. Zheng, X. Chen, R. Xu, and B. Chang, A double-graph based framework for frame semantic parsing, in Proc. 2022 Conf. North American Chapter of the Association for Computational Linguistics : Human Language Technologies, Seattle, WA, USA, 2022, pp. 4998–5011.
[19]

O. Täckström, K. Ganchev, and D. Das, Efficient inference and structured learning for semantic role labeling, Trans. Assoc. Comput. Linguist., vol. 3, pp. 29–41, 2015.

[20]
S. Swayamdipta, S. Thomson, C. Dyer, and N. A. Smith, Frame-semantic parsing with softmax-margin segmental RNNs and a syntactic scaffold, arXiv preprint arXiv: 1706.09528, 2017.
[21]
B. Yang and T. Mitchell, A joint sequential and relational model for frame-semantic parsing, in Proc. 2017 Conf. Empirical Methods in Natural Language Processing, Copenhagen, Denmark, 2017, pp. 1247–1256.
[22]
E. Bastianelli, A. Vanzo, and O. Lemon, Encoding syntactic constituency paths for frame-semantic parsing with graph convolutional networks, arXiv preprint arXiv: 2011.13210, 2020.
[23]
Z. Lin, Y. Sun, and M. Zhang, A graph-based neural model for end-to-end frame semantic parsing, in Proc. 2021 Conf. Empirical Methods in Natural Language Processing, Punta Cana, Dominican Republic, 2021, pp. 3864–3874.
[24]
T. Dozat and C. D. Manning, Deep biaffine attention for neural dependency parsing, arXiv preprint arXiv: 1611.01734, 2017.
[25]
M. Tan, R. Pang, and Q. V. Le, EfficientDet: Scalable and efficient object detection, in Proc. 2020 IEEE/CVF Conf. Computer Vision and Pattern Recognition (CVPR ), Seattle, WA, USA, 2020, pp. 10778–10787.
[26]
M. Miwa and Y. Sasaki, Modeling joint entity and relation extraction with table representation, in Proc. 2014 Conf. Empirical Methods in Natural Language Processing (EMNLP ), Doha, Qatar, 2014, pp. 1858–1869.
[27]
P. Gupta, H. Schütze, and B. Andrassy, Table filling multi-task recurrent neural network for joint entity and relation extraction, in Proc. COLING 2016, the 26 th Int. Conf. Computational Linguistics : Technical Papers, Osaka, Japan, 2016, pp. 2537–2547.
[28]
M. Zhang, Y. Zhang, and G. Fu, End-to-end neural relation extraction with global optimization, in Proc. 2017 Conf. Empirical Methods in Natural Language Processing, Copenhagen, Denmark, 2017, pp. 1730–1740.
[29]
H. Adel and H. Schütze, Global normalization of convolutional neural networks for joint entity and relation classification, in Proc. 2017 Conf. Empirical Methods in Natural Language Processing, Copenhagen, Denmark, 2017, pp. 1723–1729.
[30]
Y. M. Shang, H. Huang, and X. Mao, OneRel: Joint entity and relation extraction with one module in one step, in Proc. 36 th AAAI Conf. Artificial Intelligence, Virtual Event, 2022, pp. 11285–11293.
[31]
J. Wang and W. Lu, Two are better than one: Joint entity and relation extraction with table-sequence encoders, in Proc. 2020 Conf. Empirical Methods in Natural Language Processing (EMNLP ), Virtual Event, 2020, pp. 1706–1721.
[32]
Y. Zhang, Y. Yang, Y. Li, B. Liang, S. Chen, Y. Dang, M. Yang, and R. Xu, Boundary-driven table-filling for aspect sentiment triplet extraction, in Proc. 2022 Conf. Empirical Methods in Natural Language Processing, Abu Dhabi, United Arab Emirates, 2022, pp. 6485–6498.
[33]
J. Liu, Y. Chen, and J. Xu, Saliency as evidence: Event detection with trigger saliency attribution, in Proc. 60 th Annu. Meeting of the Association for Computational Linguistics (Volume 1 : Long Papers ), Dublin, Ireland, 2022, pp. 4573–4585.
[34]
K. He, X. Zhang, S. Ren, and J. Sun, Deep residual learning for image recognition, in Proc. 2016 IEEE Conf. Computer Vision and Pattern Recognition (CVPR ), Las Vegas, NV, USA, 2016, pp. 770–778.
[35]
J. Yu, B. Bohnet, and M. Poesio, Named entity recognition as dependency parsing, in Proc. 58 th Annu. Meeting of the Association for Computational Linguistics, Virtual Event, 2020, pp. 6470–6476.
[36]
J. Ruppenhofer, M. Ellsworth, M. R. L. Petruck, C. R. Johnson, C. F. Baker, and J. Scheffczyk, FrameNet II: Extended theory and practice, https://framenet2.icsi.berkeley.edu/docs/r1.7/book.pdf, 2016.
[37]
W. X. Zhao, K. Zhou, J. Li, T. Tang, X. Wang, Y. Hou, Y. Min, B. Zhang, J. Zhang, Z. Dong, et al., A survey of large language models, arXiv preprint arXiv: 2303.18223, 2023.
[38]
H. Touvron, L. Martin, K. Stone, P. Albert, A. Almahairi, Y. Babaei, N. Bashlykov, S. Batra, P. Bhargava, S. Bhosale, et al., Llama 2: Open foundation and fine-tuned chat models, arXiv preprint arXiv: 2307.09288, 2023.
[39]

Y. Guo, D. Zhou, X. Ruan, and J. Cao, Variational gated autoencoder-based feature extraction model for inferring disease-miRNA associations based on multiview features, Neural Networks, vol. 165, pp. 491–505, 2023.

[40]

W. Li, Y. Guo, B. Wang, and B. Yang, Learning spatiotemporal embedding with gated convolutional recurrent networks for translation initiation site prediction, Pattern Recognition, vol. 136, p. 109234, 2023.

[41]

Y. Guo, D. Zhou, P. Li, C. Li, and J. Cao, Context-Aware Poly(A) signal prediction model via deep spatial-temporal neural networks, IEEE Trans. Neural Netw. Learn. Syst., vol. 35, no. 7, pp. 8241–8253, 2024.

Tsinghua Science and Technology
Pages 1474-1495
Cite this article:
Su X, Li R, Li X, et al. EFSP-TE: End-to-End Frame-Semantic Parsing with Table Encoder. Tsinghua Science and Technology, 2025, 30(4): 1474-1495. https://doi.org/10.26599/TST.2024.9010036
Metrics & Citations  
Article History
Copyright
Rights and Permissions
Return