Abstract
The task of document-level relation extraction (RE) involves integration of information within and across multiple sentences of a document and extraction of complex semantic relations between multiple named entities. However, effective aggregation of local and nonlocal contexts information in the document continues to be a challenging research question. This study proposes a novel document-level RE model, called the multi-perspective context aggregation (MPCA), that aggregates document context information from multi-perspective at different layers. Specifically, this aggregated context information not only comes from the pre-training stage but is also reflected during node construction and classification. Experimental results show that our model achieves desirable performance on two public datasets for document-level RE and is particularly effective in extracting relations between entities with multiple mentions.
Similar content being viewed by others
References
Yu M, Yin W, Hasan KS, Santos CD, Xiang B, Zhou B (2017) Improved neural relation detection for knowledge base question answering. In: Proceedings of the 55th annual meeting of the association for computational linguistics(ACL), pp 571–581
Qiu L, Xiao Y, Qu Y, Zhou H, Li L, Zhang W, Yu Y (2019) Dynamically fused graph network for multihop reasoning. In: Proceedings of the 57th annual meeting of the association for computational linguistics(ACL), pp 6140–6150
Li J, Sun Y, Johnson RJ, Sciaky D, Wei CH, Leaman R, Lu Z (2016) BioCreative V CDR task corpus: a resource for chemical disease relation extraction. Database, 2016
Wu Y, Luo R, Leung H, Ting HF, Lam TW (2019) Renet: a deep learning approach for extracting gene-disease associations from literature. In: International conference on research in computational molecular biology (RE-COMB), pp 272–284
Beltagy I, Lo K, Cohan A (2019) SciBERT: a pretrained language model for scientific text. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP), pp 3615–3620
Xiao M, Cong L (2016) Semantic relation classification via hierarchical recurrent neural network with attention. In: Proceedings of COLING 2016, the 26th international conference on computational linguistics(COLING), pp 1254–1263
Zhang Y, Zhong V, Chen D, Angeli G, Manning CD (2017) Position-aware attention and supervised data improve slot filling. In: Proceedings of the 2017 conference on empirical methods in natural language processing(EMNLP), pp 35–45
Zhang Y, Qi P, Manning CD (2018) Graph convolution over pruned dependency trees improves relation extraction. In: Proceedings of the 2018 conference on empirical methods in natural language processing(EMNLP), pp 2205–2215
Soares LB, FitzGerald N, Ling J, Kwiatkowski T (2019) Matching the blanks: distributional similarity for relation learning. In: Proceedings of the 57th annual meeting of the association for computational linguistics(ACL), pp 2895–2905
Verga P, Strubell E, McCallum A (2018) Simultaneously self-attending to all mentions for full-abstract biological relation extraction. In: Proceedings of the 2018 conference of the North American chapter of the association for computational linguistics (NAACL), pp 872–884
Christopoulou F, Miwa M, Ananiadou S (2019) Connecting the dots: document-level neural relation extraction with edge-oriented graphs. In: Proceedings of the 2019 conference on empirical methods in natural language processing(EMNLP), pp 4925–4936
Sahu SK, Christopoulou F, Miwa M, Ananiadou S (2019) Inter-sentence relation extraction with document-level graph convolutional neural network. In: Proceedings of the 57th annual meeting of the association for computational linguistics(ACL), pp 4309–4316
Yao Y, Ye D, Li P, Han X, Lin Y, Liu Z, Sun M (2019) DocRED: a large-scale document-level relation extraction dataset. In: Proceedings of the 57th annual meeting of the association for computational linguistics(ACL), pp 764–777
Nan G, Guo Z, Sekulić I, Lu W (2020) Reasoning with latent structure refinement for document-level relation extraction. In: Proceedings of the 58th annual meeting of the association for computational linguistics(ACL), pp 1546–1557
Tang H, Cao Y, Zhang Z, Cao J, Fang F, Wang S, Yin P (2020) HIN:hierarchical inference networkfor document-level relation extraction. In: Proceedings of the 2019 Pacific-Asia conference on knowledge discovery and data mining(PAKDD), pp 197–209
Wang D, Hu W, Cao E, Sun W (2020) Global-to-local neural networks for document-level relation extraction. In: Proceedings of the 2020 conference on empirical methods in natural language processing(EMNLP), pp 3711–3721
Xu W, Chen K, Zhao T (2021) Document-level relation extraction with reconstruction. In: The 35th AAAI conference on artificial intelligence (AAAI)
Liu Y, Lapata M (2018) Learning structured text representations. In: Transactions of the association for computational linguistics(TACL), pp 63–75
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780
Chung J, Gulcehre C, Cho K, Bengio Y (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling. In: Proceedings of the 2014 international conference and workshop on neural information processing systems(NIPS), pp 1–9
Mikolov T, Sutskever I, Chen K, Corrado GS, Dean J (2013) Distributed representations of words and phrases and their compositionality. Neur Inform, 3111–3119
Pennington J, Socher R, Manning CD (2014) Glove: global vectors for word representation. In: proceedings of the 2014 conference on empirical methods in natural language processing(EMNLP), pp 1532–1543
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Polosukhin I (2017) Attention is all you need. Neural information, 5998–6008
Tenney I, Das D, Pavlick E (2019) BERT rediscovers the classical NLP pipeline. In: Proceedings of the 57th annual meeting of the association for computational linguistics(ACL), pp 4593–4601
Devlin J, Chang M, Lee K, Toutanova K (2019) BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics(NAACL), pp 4171–4186
Zhou W, Huang K, Ma T, Huang J (2021) Document-level relation extraction with adaptive thresholding and localized context pooling. In: Proceedings of the AAAI conference on artificial intelligence(AAAI), pp 14612–14620
Wang H, Focke C, Sylvester R, Mishra N, Wang W (2019) Fine-tune bert for DocRED with two-step process. arXiv preprint arXiv:1909.11898
Schlichtkrull M, Kipf TN, Bloem P, Berg RVD, Titov I, Welling M (2018) Modeling relational data with graph convolutional networks. In: European semantic web conference(ESWC), pp 593–607
Sorokin D, Gurevych I (2017) Context-aware representations for knowledge base relation extraction. In: Proceedings of the 2017 conference on empirical methods in natural language processing(EMNLP), pp 1784–1789
Jia R, Wong C, Poon H (2019) Document-level N-ary relation extraction with multiscale representation learning. In: Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics(NAACL), pp 3693–3704
Mou L, Men R, Li G, Xu Y, Zhang L, Yan R, Jin Z (2016) Natural language inference by tree-based convolution and heuristic matching. In: Proceedings of the 54th annual meeting of the association for computational linguistics(ACL), pp 130–136
Hendrickx I, Kim SN, Kozareva Z, Nakov P, Séaghdha DO, Padó S, Szpakowicz S (2009) Semeval-2010 task 8: multi-way classification of semantic relations between pairs of nominals. In: Proceedings of the 2009 conference of the North American chapter of the association for computational linguistics(NAACL), pp 33–38
Wang H, Qin K, Lu G, Yin J, Zakari RY, Owusu JW (2021) Document-level relation extraction using evidence reasoning on RST-GRAPH, vol 228, p 107274
Fukushima K (1980) Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position, vol 36, pp 193–202
Schuster M, Paliwal KK (1997) Bidirectional recurrent neural networks, vol 45, pp 2673–2681
Veličković P, Cucurull G, Casanova A, Romero A, Lio P, Bengio Y (2018) Graph attention networks. In: International conference on learning representations(ILCR)
Han X, Wang L (2020) A novel document-level relation extraction method based on BERT and entity information. IEEE Access 8:96912–96919
Loshchilov I, Hutter F (2019) Decoupled weight decay regularization. In: International conference on learning representations(ILCR)
Paszke A, Gross S, Chintala S, Chanan G, Yang E, DeVito Z, Lerer A (2017) Automatic differentiation in pytorch. In: NIPS-W
Jiang F, Li P, Zhu Q (2021) Recognizing Chinese discourse relations based on multi-perspective and hierarchical modeling. In: 2021 International joint conference on neural networks (IJCNN), pp 1–8
Allaway E, Wang S, Ballesteros M (2021) Sequential cross-document coreference resolution. arXiv preprint arXiv:2104.08413
Lin JCW, Shao Y, Djenouri Y, Yun U (2021) ASRNN: a recurrent neural network with an attention model for sequence labeling, vol 212, p 106548
Xiong Y, Feng Y, Wu H, Kamigaito H, Okumura M (2021) Fusing label embedding into BERT: an efficient improvement for text classification. In: Findings of the association for computational linguistics(ACL-IJCNLP), pp 1743–1750
Xu B, Wang Q, Lyu Y, Zhu Y, Mao Z (2021) Entity structure within and throughout: modeling mention dependencies for document-level relation extraction. In: The 35th AAAI conference on artificial intelligence (AAAI)
Acknowledgments
This work is supported by the Science and Technology Research Project of Henan Province (No. 192102210129).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Ding, X., Zhou, G. & Zhu, T. Multi-perspective context aggregation for document-level relation extraction. Appl Intell 53, 6926–6935 (2023). https://doi.org/10.1007/s10489-022-03731-w
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-03731-w