Abstract
Document-level relation extraction (DocRE) aims to extract relations among entities across multiple sentences within a document by using reasoning skills (i.e., pattern recognition, logical reasoning, coreference reasoning, etc.) related to the reasoning paths between two entities. However, most of the advanced DocRE models only attend to the feature representations of two entities to determine their relation, and do not consider one complete reasoning path from one entity to another entity, which may hinder the accuracy of relation extraction. To address this issue, this article proposes a novel method to capture this reasoning path from one entity to another entity, thereby better simulating reasoning skills to classify relation between two entities. Furthermore, we introduce an additional attention layer to summarize multiple reasoning paths for further enhancing the performance of the DocRE model. Experimental results on a large-scale document-level dataset show that the proposed approach achieved a significant performance improvement on a strong heterogeneous graph-based baseline.
- [1] . 2019. Matching the blanks: Distributional similarity for relation learning. In Proceedings of the Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Florence, Italy,2895–2905. Google Scholar
Cross Ref
- [2] . 2019. Connecting the dots: Document-level neural relation extraction with edge-oriented graphs. In Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Association for Computational Linguistics, Hong Kong, China,4925–4936. Google Scholar
Cross Ref
- [3] . 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, Minneapolis, Minnesota,4171–4186. Google Scholar
Cross Ref
- [4] . 2020. Multi-sentence argument linking. In Proceedings of the Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online,8057–8077. Google Scholar
Cross Ref
- [5] . 2019. Attention guided graph convolutional networks for relation extraction. In Proceedings of the Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Florence, Italy,241–251. Google Scholar
Cross Ref
- [6] . 2019. Neural relation extraction within and across sentence boundaries. In Proceedings of the AAAI Conference on Artificial Intelligence. AAAI Press, Hawaii, USA,6513–6520. Google Scholar
Digital Library
- [7] . 1997. Long short-term memory. Neural Computation 9, 8 (1997),1735–1780. https://direct.mit.edu/neco/article-abstract/9/8/1735/6109/Long-Short-Term-Memory?redirectedFrom=fulltext.Google Scholar
Digital Library
- [8] . 2016. BioCreative V CDR task corpus: A resource for chemical disease relation extraction.. In Database : The Journal of Biological Databases and Curation. PubMed, Online,1–10. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4860626/pdf/baw068.pdf.Google Scholar
- [9] . 2018. Chinese open relation extraction and knowledge base establishment. ACM Transactions on Asian and Low-Resource Language Information Processing 17, 3, Article
15 (2018), 22 pages. Google ScholarDigital Library
- [10] . 2013. Convolution neural network for relation extraction. In Proceedings of the International Conference on Advanced Data Mining and Applications (ADMA 2013). Springer-Verlag, Berlin,231–242. Google Scholar
Digital Library
- [11] . 2020. Joint model of entity recognition and relation extraction with self-attention mechanism. ACM Transactions on Asian and Low-Resource Language Information Processing 19, 4, Article
59 (2020), 19 pages. Google ScholarDigital Library
- [12] . 2020. A simple and effective unified encoder for document-level machine translation. In Proceedings of the Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online,3505–3511. Google Scholar
Cross Ref
- [13] . 2021. A neural edge-editing approach for document-level relation graph extraction. In Findings of the Association for Computational Linguistics: ACL-IJCNLP. Association for Computational Linguistics, Online,2653–2662. Google Scholar
Cross Ref
- [14] . 2020. Reasoning with latent structure refinement for document-level relation extraction. In Proceedings of the Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online,1546–1557. Google Scholar
Cross Ref
- [15] . 2017. Distant supervision for relation extraction beyond the sentence boundary. In Proceedings of the Conference of the European Chapter of the Association for Computational Linguistics, Vol. 1. Association for Computational Linguistics, Valencia, Spain,1171–1182. https://www.aclweb.org/anthology/E17-1110.Google Scholar
Cross Ref
- [16] . 2019. Inter-sentence relation extraction with document-level graph convolutional neural network. In Proceedings of the Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Florence, Italy,4309–4316. Google Scholar
Cross Ref
- [17] . 2009. The graph neural network model. IEEE Transactions on Neural Networks 20, 1 (2009),61–80. Google Scholar
Digital Library
- [18] . 2012. Semantic compositionality through recursive matrix-vector spaces. In Proceedings of the Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. Association for Computational Linguistics, Jeju Island, Korea,1201–1211. https://aclanthology.org/D12-1110.Google Scholar
- [19] . 2019. Leveraging dependency forest for neural medical relation extraction. In Proceedings of the Conference on Empirical Methods in Natural Language Processing and the International Joint Conference on Natural Language Processing. Association for Computational Linguistics, Hong Kong, China,208–218. Google Scholar
Cross Ref
- [20] . 2018. Global relation embedding for relation extraction. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, New Orleans, LA,820–830. Google Scholar
Cross Ref
- [21] . 2020. HIN: Hierarchical inference network for document-level relation extraction. In Advances in Knowledge Discovery and Data Mining. Springer-Verlag, Berlin,197–209. Google Scholar
Digital Library
- [22] . 2017. Attention is all you need. In Advances in Neural Information Processing Systems, , , , , , , and (Eds.), Vol. 30. Curran Associates, Inc., California,5998–6008. https://proceedings.neurips.cc/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf.Google Scholar
- [23] . 2018. Graph attention networks. In Proceedings of the International Conference on Learning Representations. OpenReview.net, Online,12 pages. https://openreview.net/forum?id=rJXMpikCZ.Google Scholar
- [24] . 2019. Fine-tune BERT for DocRED with two-step process. ArXiv abs/1909.11898 (2019),9 pages. https://arxiv.org/pdf/1909.11898.pdf.Google Scholar
- [25] . 2020. An extensible framework of leveraging syntactic skeleton for semantic relation classification. ACM Transactions on Asian and Low-Resource Language Information Processing 19, 6, Article
77 (2020), 21 pages. Google ScholarDigital Library
- [26] . 2016. Relation classification via multi-level attention CNNs. In Proceedings of the Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Berlin, Germany,1298–1307. Google Scholar
Cross Ref
- [27] . 2020. A novel cascade binary tagging framework for relational triple extraction. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online,1476–1488. https://www.aclweb.org/anthology/2020.acl-main.136.Google Scholar
Cross Ref
- [28] . 2019. A comprehensive survey on graph neural networks. IEEE Transactions on Neural Networks and Learning Systems 32 (2019),4–24. https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9046288&tag=1.Google Scholar
Cross Ref
- [29] . 2022. SAIS: Supervising and augmenting intermediate steps for document-level relation extraction. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, Seattle, United States,2395–2409. Google Scholar
Cross Ref
- [30] . 2022. Eider: Empowering document-level relation extraction with efficient evidence extraction and inference-stage fusion. In Findings of the Association for Computational Linguistics: ACL 2022. Association for Computational Linguistics, Dublin, Ireland,257–268. Google Scholar
Cross Ref
- [31] . 2020. Self-attention guided copy mechanism for abstractive summarization. In Proceedings of the Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online,1355–1362. Google Scholar
Cross Ref
- [32] . 2021. Document-level relation extraction with reconstruction. In Proceedings of the AAAI Conference on Artificial Intelligence 35, 16 (2021),14167–14175. https://ojs.aaai.org/index.php/AAAI/article/view/17667.Google Scholar
Cross Ref
- [33] . 2021. Entity concept-enhanced few-shot relation extraction. In Proceedings of the Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. Association for Computational Linguistics, Online,987–991. Google Scholar
Cross Ref
- [34] . 2019. DocRED: A large-scale document-level relation extraction dataset. In Proceedings of the Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Florence, Italy,764–777. Google Scholar
Cross Ref
- [35] . 2014. Relation classification via convolutional deep neural network. In Proceedings of the International Conference on Computational Linguistics. Dublin City University and Association for Computational Linguistics, Dublin, Ireland,2335–2344. https://www.aclweb.org/anthology/C14-1220.Google Scholar
- [36] . 2021. SIRE: Separate intra- and inter-sentential reasoning for document-level relation extraction. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. Association for Computational Linguistics, Online,524–534. Google Scholar
Cross Ref
- [37] . 2020. Double graph based reasoning for document-level relation extraction. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Online,1630–1640. https://www.aclweb.org/anthology/2020.emnlp-main.127.Google Scholar
Cross Ref
- [38] . 2021. Open hierarchical relation extraction. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, Online,5682–5693. Google Scholar
Cross Ref
- [39] . 2021. Entity relation extraction as dependency parsing in visually rich documents. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic,2759–2768. Google Scholar
Cross Ref
- [40] . 2018. Graph convolution over pruned dependency trees improves relation extraction. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Brussels, Belgium,2205–2215. Google Scholar
Cross Ref
- [41] . 2021. Document-level relation extraction with adaptive thresholding and localized context pooling. In Proceedings of the AAAI Conference on Artificial Intelligence 35, 16 (2021),14612–14620. https://ojs.aaai.org/index.php/AAAI/article/view/17717.Google Scholar
Cross Ref
Index Terms
Document-Level Relation Extraction with Path Reasoning
Recommendations
Evidence-aware Document-level Relation Extraction
CIKM '22: Proceedings of the 31st ACM International Conference on Information & Knowledge ManagementDocument-level Relation Extraction (RE) is a promising task aiming at identifying relations of multiple entity pairs in a document. However, in most cases, a relational fact can be expressed enough via a small subset of sentences from the document, ...
Improving Graph-based Document-Level Relation Extraction Model with Novel Graph Structure
CIKM '22: Proceedings of the 31st ACM International Conference on Information & Knowledge ManagementDocument-level relation extraction is a natural language processing task for extracting relations among entities in a document. Compared with sentence-level relation extraction, there are more challenges to document-level relation extraction. To acquire ...
Document-level Relation Extraction via Separate Relation Representation and Logical Reasoning
Document-level relation extraction (RE) extends the identification of entity/mentions’ relation from the single sentence to the long document. It is more realistic and poses new challenges to relation representation and reasoning skills. In this paper, we ...






Comments