Abstract
Document-level relation extraction aims to extract relations from multiple sentences in a document. However, it remains challenging to obtain rich semantic information across multiple sentences for relation prediction. In this paper, a multi-granularity relation extraction (MGRE) neural network is proposed, which integrates multiple granularity semantic features (i.e., entity level, sentence level and document level), to capture the semantic interactions among entities and sentences in a document. For entities, the shortest dependency path is utilized to obtain head-to-tail entity representations, which is further used for acquiring the relation between entity pairs through a translation strategy. Then, at the sentence level, a convolutional neural network is used to extract semantic features for each sentence. While for the documents, an attention mechanism is adopted to fuse multiple sentence-level feature vectors into document-level semantic features. Finally, entity representation and document representation are combined into a holistic representation for relation prediction. Extensive experiments are conducted on the DocRED dataset against state-of-the-art methods, and the comparative results demonstrate the superiority of MGRE on document-level relation extraction.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bordes, A., Usunier, N., García-Durán, A., et al.: Translating embeddings for modeling multi-relational data. In: NeurIPS (2013)
Christopoulou, F., Miwa, M., Ananiadou, S.: Connecting the dots: document-level neural relation extraction with edge-oriented graphs. In: EMNLP (2019)
Devlin, J., Chang, M.W., Lee, K., et al.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL, pp. 4171–4186 (2019)
Goyal, P., Dollá¡r, P., Girshick, R., et al.: Accurate, large minibatch SGD: training imagenet in 1 hour (2018)
Gu, J., Sun, F., Qian, L., et al.: Chemical-induced disease relation extraction via convolutional neural network. Databases 2017, bax024 (2017)
Gupta, P., Rajaram, S., Schütze, H., et al.: Neural relation extraction within and across sentence boundaries. In: AAAI, pp. 6513–6520 (2019)
Kim, K., Hur, Y., Kim, G., et al.: GREG: a global level relation extraction with knowledge graph embedding. Appl. Sci. 10(3) (2020)
Li, B., Ye, W., Sheng, Z., et al.: Graph enhanced dual attention network for document-level relation extraction. In: ACL, pp. 1551–1560 (2020)
Lin, Y., Shen, S., Liu, Z., et al.: Neural relation extraction with selective attention over instances. In: ACL (2016)
Lin, Z., Feng, M., dos Santos, C.N., et al.: A structured self-attentive sentence embedding. In: ICLR (2017)
Liu, Y., Wei, F., Li, S., et al.: A dependency-based neural network for relation classification. In: ACL, pp. 285–290 (2015)
Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2019)
Lu, C., Zhang, R., Sun, K., Kim, J., Zhang, C., Mao, Y.: Anaphor assisted document-level relation extraction (2023)
Ma, Y., Wang, A., Okazaki, N.: DREEAM: guiding attention with evidence for improving document-level relation extraction. In: EACL (2023)
Miwa, M., Bansal, M.: End-to-end relation extraction using LSTMs on sequences and tree structures. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pp. 1105–1116 (2016)
Nan, G., Guo, Z., Sekulic, I., et al.: Reasoning with latent structure refinement for document-level relation extraction. In: ACL, pp. 1546–1557 (2020)
Nguyen, D.Q., Verspoor, K.: Convolutional neural networks for chemical-disease relation extraction are improved with character-based word embeddings. In: The 18th Workshop on Biomedical Natural Language Processing (2018)
Pennington, J., Socher, R., Manning, C.D.: GloVe: global vectors for word representation. In: EMNLP, pp. 1532–1543 (2014)
dos Santos, C.N., Xiang, B., Zhou, B.: Classifying relations by ranking with convolutional neural networks. In: ACL (2015)
Schuster, M., Paliwal, K.: Bidirectional recurrent neural networks. IEEE Trans. Signal Process. 45(11), 2673–2681 (1997)
Socher, R., Huval, B., Manning, C.D., et al.: Semantic compositionality through recursive matrix-vector spaces. In: EMNLP (2012)
Tan, Q., He, R., Bing, L., Ng, H.T.: Document-level relation extraction with adaptive focal loss and knowledge distillation. In: ACL (2022)
Tang, H., et al.: HIN: hierarchical inference network for document-level relation extraction. In: Lauw, H.W., Wong, R.C.-W., Ntoulas, A., Lim, E.-P., Ng, S.-K., Pan, S.J. (eds.) PAKDD 2020. LNCS (LNAI), vol. 12084, pp. 197–209. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-47426-3_16
Verga, P., Strubell, E., McCallum, A.: Simultaneously self-attending to all mentions for full-abstract biological relation extraction. In: NAACL, pp. 872–884 (2018)
Wang, H., Focke, C., Sylvester, R., et al.: Fine-tune BERT for docRED with two-step process. ArXiv abs/1909.11898 (2019)
Wang, L., Cao, Z., de Melo, G., el al.: Relation classification via multi-level attention CNNs. In: ACL (2016)
Xie, Y., Shen, J., Li, S., Mao, Y., Han, J.: Eider: empowering document-level relation extraction with efficient evidence extraction and inference-stage fusion. In: Findings of the Association for Computational Linguistics: ACL 2022 (2022)
Xu, B., Wang, Q., Lyu, Y., et al.: Entity structure within and throughout: modeling mention dependencies for document-level relation extraction (2021)
Xu, W., Chen, K., Mou, L., Zhao, T.: Document-level relation extraction with sentences importance estimation and focusing. In: NAACL (2022)
Yao, Y., Ye, D., Li, P., et al.: DocRED: a large-scale document-level relation extraction dataset. In: ACL, pp. 764–777 (2019)
Zeng, D., Liu, K., Lai, S., et al.: Relation classification via convolutional deep neural network. In: ACL, pp. 2335–2344 (2014)
Zeng, S., Xu, R., Chang, B., et al.: Double graph based reasoning for document-level relation extraction. In: EMNLP (2020)
Zhang, L., Su, J., Chen, Y., Miao, Z., Zijun, M., Hu, Q., Shi, X.: Towards better document-level relation extraction via iterative inference. In: EMNLP (2022)
Zhou, H., Xu, Y., Yao, W., et al.: Global context-enhanced graph convolutional networks for document-level relation extraction. In: ACL, pp. 5259–5270 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chen, X., Wang, P. (2024). Multi-granularity Neural Networks for Document-Level Relation Extraction. In: Zhang, W., Tung, A., Zheng, Z., Yang, Z., Wang, X., Guo, H. (eds) Web and Big Data. APWeb-WAIM 2024. Lecture Notes in Computer Science, vol 14965. Springer, Singapore. https://doi.org/10.1007/978-981-97-7244-5_7
Download citation
DOI: https://doi.org/10.1007/978-981-97-7244-5_7
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-7243-8
Online ISBN: 978-981-97-7244-5
eBook Packages: Computer ScienceComputer Science (R0)