基于证据和图推理的文档级关系抽取方法: 以医学关系为例

doi:10.19678/j.issn.1000-3428.0068877

计算机工程 ›› 2025, Vol. 51 ›› Issue (1): 106-117. doi: 10.19678/j.issn.1000-3428.0068877

基于证据和图推理的文档级关系抽取方法: 以医学关系为例

周雪阳¹^,², 傅启明¹^,²^,*(), 陈建平²^,³^,⁴, 陈延明⁵, 陆悠¹^,², 王蕴哲¹^,²

1. 苏州科技大学电子与信息工程学院, 江苏苏州 215009
2. 苏州科技大学江苏省建筑智慧节能重点实验室, 江苏苏州 215009
3. 苏州科技大学建筑与城市规划学院, 江苏苏州 215009
4. 重庆工业大数据创新中心有限公司, 重庆 400707
5. 苏州大学附属第二医院神经外科, 江苏苏州 215004

收稿日期:2023-11-20 出版日期:2025-01-15 发布日期:2024-04-25
通讯作者: 傅启明
基金资助:
国家重点研发计划(2020YFC2006602); 国家自然科学基金(62102278); 国家自然科学基金(62072324); 江苏省高等学校自然科学研究项目(21KJA520005); 江苏省重点研发计划(BE2020026); 江苏省研究生教育教学改革项目; 江苏省研究生科研与实践创新计划项目(KYCX23_3321)

Document-Level Relation Extraction Method Based on Evidence and Graph Inference: A Case Study of Medical Relationships

ZHOU Xueyang¹^,², FU Qiming¹^,²^,*(), CHEN Jianping²^,³^,⁴, CHEN Yanming⁵, LU You¹^,², WANG Yunzhe¹^,²

1. Electronic and Information Engineering, Suzhou University of Science and Technology, Suzhou 215009, Jiangsu, China
2. Jiangsu Province Key Laboratory of Intelligent Building Energy Efficiency, Suzhou University of Science and Technology, Suzhou 215009, Jiangsu, China
3. Architecture and Urban Planning, Suzhou University of Science and Technology, Suzhou 215009, Jiangsu, China
4. Chongqing Industrial Big Data Innovation Center Co., Ltd., Chongqing 400707, China
5. Department of Neurosurgery, The Second Affiliated Hospital of Soochow University, Suzhou 215004, Jiangsu, China

Received:2023-11-20 Online:2025-01-15 Published:2024-04-25
Contact: FU Qiming

摘要/Abstract

摘要：

针对生物医学文献句式冗长、实体密集从而导致关系抽取复杂度高、难度大的问题, 提出一种证据路径增强的图推理框架(EPE-GR)。首先建立一种引入结构化偏差的图注意力机制(B-GAT)增强图推理中信息聚合的指向性, 结合提及级和实体级图建模学习全局交互特征和局部依赖信息; 其次使用启发式搜索聚焦证据句子, 同时构建一种基于掩膜多头注意力(MMHA)机制的路径推理结构, 强化非邻居证据句子之间的相关性并缓解细粒度证据编码带来的复杂度剧增的问题; 最后协同全局、局部和路径推理预测实体之间的语义关系。与已有方法相比, EPE-GR在药物-突变相互作用(DMI)数据集和化学物质诱导疾病(CDR)数据集上都获得了最佳的性能, 前者在二分类和多分类任务的设定下相比次优方法准确率分别提高了5.65和5.13百分点, 后者F1值提高了2.85百分点, 证明所提方法是一个有效的生物医学文档级关系抽取方法且具有较好的泛化能力。此外, 通过进一步的实验表明所提出的关系依赖建模和证据路径推理机制能够有效提升模型推理句间关系的能力。

关键词: 关系抽取, 图推理, 路径推理, 证据增强, 图注意力机制, 多头注意力机制

Abstract:

To address the challenges of complex and difficult relation extraction caused by long sentences and entity density in biomedical literature, this study proposes an Evidence Path Enhanced Graphical Reasoning Framework (EPE-GR). First, a graph attention mechanism that introduces structured bias (B-GAT) is established to enhance the directionality of information aggregation, combined with mention- and entity-level graph modeling to capture global and local features. Second, a heuristic search is used to focus on evidence sentences, and a path inference structure based on a mask multi-head attention mechanism is constructed to strengthen the correlation between non-neighbor evidence sentences and alleviate the complexity surge caused by fine-grained evidence encoding. Finally, global, local, and path reasoning are collaboratively used to predict semantic relations between entities. Compared to existing methods, EPE-GR demonstrates superior performance on Drug-Mutation Interaction (DMI) dataset and Chemical Induced Disease (CDR) dataset. For DMIs, the proposed framework improves accuracy by 5.65 percentage points in binary classification and 5.13 percentage points in multi-classification. For CDRs, the F1 value increases by 2.85 percentage points. These results confirm that EPE-GR is an effective document-level biomedical relationship extraction method with strong generalization ability. Further experiments highlight the effectiveness of the proposed relationship dependency modeling and evidence path inference mechanism in enhancing inter-sentence relation model inference.

Key words: relation extraction, graphical reasoning, path reasoning, evidence enhancing, graph attention mechanism, multi-head attention mechanism

周雪阳, 傅启明, 陈建平, 陈延明, 陆悠, 王蕴哲. 基于证据和图推理的文档级关系抽取方法: 以医学关系为例[J]. 计算机工程, 2025, 51(1): 106-117.

ZHOU Xueyang, FU Qiming, CHEN Jianping, CHEN Yanming, LU You, WANG Yunzhe. Document-Level Relation Extraction Method Based on Evidence and Graph Inference: A Case Study of Medical Relationships[J]. Computer Engineering, 2025, 51(1): 106-117.

https://www.ecice06.com/CN/Y2025/V51/I1/106

图/表 12

图1 EPE-GR框架图

Fig.1 EPE-GR framework diagram

图2 图推理模块

Fig.2 Graph reasoning module

图3 实体水平交互图

Fig.3 Entity-level interaction graph

图4 提及水平交互图

Fig.4 Mentions-level interaction graph

图5 证据路径推理模块

Fig.5 Evidence path reasoning module

图6 有无通信模块下EPE-GR的性能比较

Fig.6 Performance comparison of EPE-GR with and without communication module

图7 案例分析

Fig.7 Case analysis

参考文献 34

1	张志昌, 周侗, 张瑞芳, 等. 融合双向GRU与注意力机制的医疗实体关系识别. 计算机工程, 2020, 46 (6): 296- 302. URL
	ZHANG Z C , ZHOU T , ZHANG R F , et al. Medical entity relation recognition combining bidirectional GRU and attention. Computer Engineering, 2020, 46 (6): 296- 302. URL
2	陈梦萱, 陈艳平, 扈应, 等. 基于词义增强的生物医学命名实体识别方法. 计算机工程, 2023, 49 (10): 305- 312. URL
	CHEN M X , CHEN Y P , HU Y , et al. Biomedical named entity recognition method based on word meaning enhancement. Computer Engineering, 2023, 49 (10): 305- 312. URL
3	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[EB/OL]. [2023-05-10]. https://arxiv.org/abs/1706.03762.
4	CHRISTOPOULOU F, MIWA M, ANANIADOU S. Connecting the dots: document-level neural relation extraction with edge-oriented graphs[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing(EMNLP-IJCNLP). Stroudsburg, USA: Association for Computational Linguistics, 2019: 4925-4936.
5	NAN G S, GUO Z J, SEKULIC I, et al. Reasoning with latent structure refinement for document-level relation extraction[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: Association for Computational Linguistics, 2020: 1546-1557.
6	LI B, YE W, SHENG Z H, et al. Graph enhanced dual attention network for document-level relation extraction[C]//Proceedings of the 28th International Conference on Computational Linguistics. Stroudsburg, USA: International Committee on Computational Linguistics, 2020: 1551-1560.
7	ZENG S, XU R X, CHANG B B, et al. Double graph based reasoning for document-level relation extraction[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing(EMNLP). Stroudsburg, USA: Association for Computational Linguistics, 2020: 1630-1640.
8	LI J Y, XU K, LI F, et al. MRN: a locally and globally mention-based reasoning network for document-level relation extraction[C]//Proceedings of ACL-IJCNLP 2021. Stroudsburg, USA: Association for Computational Linguistics, 2021: 1359-1370.
9	HUANG L , LIN J C , LI X T , et al. EGFI: drug-drug interaction extraction and generation with fusion of enriched entity and sentence information. Briefings in Bioinformatics, 2022, 23 (1): bbab451. doi: 10.1093/bib/bbab451
10	YE D M, LIN Y K, DU J J, et al. Coreferential reasoning learning for language representation[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing(EMNLP). Stroudsburg, USA: Association for Computational Linguistics, 2020: 7170-7186
11	XU B F , WANG Q , LYU Y J , et al. Entity structure within and throughout: modeling mention dependencies for document-level relation extraction. Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35 (16): 14149- 14157. doi: 10.1609/aaai.v35i16.17665
12	ZHOU W X , HUANG K , MA T Y , et al. Document-level relation extraction with adaptive thresholding and localized context pooling. Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35 (16): 14612- 14620. doi: 10.1609/aaai.v35i16.17717
13	HUANG Q Z, ZHU S Q, FENG Y S, et al. Three sentences are all you need: local path enhanced document relation extraction[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing(Volume 2: Short Papers). Stroudsburg, USA: Association for Computational Linguistics, 2021: 998-1004.
14	XU W, CHEN K H, MOU L L, et al. Document-level relation extraction with sentences importance estimation and focusing[C]//Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg, USA: Association for Computational Linguistics, 2022: 2920-2929.
15	VELICKOVIC P, CUCURULL G, CASANOVA A, et al. Graph attention networks[EB/OL]. [2023-05-10]. https://arxiv.org/abs/1710.10903.
16	YAO Y, YE D M, LI P, et al. DocRED: a large-scale document-level relation extraction dataset[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: Association for Computational Linguistics, 2019: 764-777.
17	PENG N Y , POON H , QUIRK C , et al. Cross-sentence N-ary relation extraction with graph LSTMs. Transactions of the Association for Computational Linguistics, 2017, 5, 101- 115. doi: 10.1162/tacl_a_00049
18	LI J , SUN Y P , JOHNSON R J , et al. BioCreative V CDR task corpus: a resource for chemical disease relation extraction. Database, 2016, 2016, baw068. doi: 10.1093/database/baw068
19	SONG L F, ZHANG Y, WANG Z G, et al. N-ary relation extraction using graph-state LSTM[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: Association for Computational Linguistics, 2018: 2226-2235.
20	ZHANG Y H, QI P, MANNING C D. Graph convolution over pruned dependency trees improves relation extraction[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing(EMNLP). Stroudsburg, USA: Association for Computational Linguistics, 2018: 2205-2215.
21	MANDYA A, BOLLEGALA D, COENEN F, et al. Combining long short term memory and convolutional neural network for cross-sentence n-ary relation extraction[EB/OL]. [2023-05-10]. https://arxiv.org/abs/1811.00845.
22	GUO Z J, ZHANG Y, LU W. Attention guided graph convolutional networks for relation extraction[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: Association for Computational Linguistics, 2019: 241-251.
23	DEVLIN J, CHANG M W, LEE K, et al, BERT: pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg, USA: Association for Computational Linguistics, 2019: 4171-4186.
24	PENG Y F, YAN S K, LU Z Y. Transfer learning in biomedical natural language processing: an evaluation of BERT and ELMo on ten benchmarking datasets[C]//Proceedings of the 18th BioNLP Workshop and Shared Task. Stroudsburg, USA: Association for Computational Linguistics, 2019: 58-65.
25	JIANG Y , ZHOU Y , TU K W . Learning and evaluation of latent dependency forest models. Neural Computing and Applications, 2019, 31 (10): 6795- 6805. doi: 10.1007/s00521-018-3504-3
26	ZHAO L L , XU W R , GAO S , et al. Cross-sentence N-ary relation classification using LSTMs on graph and sequence structures. Knowledge-Based Systems, 2020, 207, 106266. doi: 10.1016/j.knosys.2020.106266
27	ZHAO D , WANG J , LIN H F , et al. Biomedical cross-sentence relation extraction via multihead attention and graph convolutional networks. Applied Soft Computing, 2021, 104, 107230. doi: 10.1016/j.asoc.2021.107230
28	LAI P T , LU Z Y . BERT-GT: cross-sentence n-ary relation extraction with BERT and graph transformer. Bioinformatics, 2021, 36 (24): 5678- 5685. doi: 10.1093/bioinformatics/btaa1087
29	CHEN X Y , ZHANG M , XIONG S W , et al. On the form of parsed sentences for relation extraction. Knowledge-Based Systems, 2022, 251, 109184. doi: 10.1016/j.knosys.2022.109184
30	LI H D , YANG M , CHEN Q C , et al. Chemical-induced disease extraction via recurrent piecewise convolutional neural networks. BMC Medical Informatics and Decision Making, 2018, 18 (Suppl 2): 60.
31	VERGA P, STRUBELL E, MCCALLUM A. Simultaneously self-attending to all mentions for full-abstract biological relation extraction[C]//Proceedings of 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg, USA: Association for Computational Linguistics, 2018, 872-884.
32	BELTAGY I, LO K, COHAN A. SciBERT: a pretrained language model for scientific text[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing(EMNLP-IJCNLP). Stroudsburg, USA: Association for Computational Linguistics, 2019, 3615-3620.
33	ZHANG Z Y, YU B W, SHU X B, et al. Document-level relation extraction with dual-tier heterogeneous graph[C]//Proceedings of the 28th International Conference on Computational Linguistics. Stroudsburg, USA: International Committee on Computational Linguistics, 2020: 1630-1641.
34	袁泉, 徐雲鹏, 唐成亮. 基于路径标签的文档级关系抽取方法. 计算机应用, 2023, 43 (4): 1029- 1035.
	YUAN Q , XU Y P , TANG C L . Document-level relation extraction method based on path labels. Journal of Computer Applications, 2023, 43 (4): 1029- 1035.

[1]	代巍, 王丰羽, 冀常鹏. 基于情感增强与双图卷积网络的方面级情感分析[J]. 计算机工程, 2024, 50(5): 120-127.
[2]	曹渝昆, 程宇, 何祯奕, 徐康乐, 颜家洛, 李云峰. 文档上下文异构表示的句子级关系抽取方法[J]. 计算机工程, 2024, 50(5): 111-119.
[3]	吴海鹏, 钱育蓉, 冷洪勇. 基于双向注意力机制的多模态关系抽取[J]. 计算机工程, 2024, 50(4): 160-167.
[4]	王明虎, 石智奎, 苏佳, 张新生. 基于RoBERTa和图增强Transformer的序列推荐方法[J]. 计算机工程, 2024, 50(4): 121-131.
[5]	李敬灿, 肖萃林, 覃晓婷, 谢夏. 基于大语言模型与语义增强的文本关系抽取算法[J]. 计算机工程, 2024, 50(4): 87-94.
[6]	廖涛, 张国畅, 张顺香. 基于双粒度图的文档级关系抽取[J]. 计算机工程, 2024, 50(10): 164-173.
[7]	任义, 苏博, 袁帅. 教育领域下多维度特征命名实体识别方法[J]. 计算机工程, 2024, 50(10): 110-118.
[8]	马建红, 龚天, 姚爽. 基于证据句与图卷积网络的文档级关系抽取[J]. 计算机工程, 2023, 49(8): 104-110.
[9]	刘昊鑫, 董超, 勾智楠, 高凯. 融合混合表征的小样本关系抽取方法[J]. 计算机工程, 2023, 49(8): 63-68.
[10]	廖涛, 孙皓洁, 张顺香. 基于跨度和特征融合的实体关系联合抽取模型[J]. 计算机工程, 2023, 49(6): 107-114.
[11]	吴雪莹, 段友祥, 昌伦杰, 李世银, 孙歧峰. 面向地质领域的实体关系联合抽取研究[J]. 计算机工程, 2023, 49(3): 121-127.
[12]	杨振宇, 王磊, 马博, 杨雅婷, 董瑞, 艾孜麦提·艾瓦尼尔, 王震. 一种针对维汉的跨语言远程监督方法[J]. 计算机工程, 2023, 49(2): 271-278.
[13]	衡红军, 范昱辰, 王家亮. 基于Transformer的多方面特征编码图像描述生成算法[J]. 计算机工程, 2023, 49(2): 199-205.
[14]	杨红菊, 靳新宇. 一个实体关系与事件抽取的通用模型[J]. 计算机工程, 2023, 49(2): 143-149.
[15]	王雨燕, 赵佳鹏, 时金桥, 申立艳, 刘洪梦, 杨燕燕. 暗网网页用户身份信息聚合方法[J]. 计算机工程, 2023, 49(11): 187-194, 210.

选择文件类型/文献管理软件名称

选择包含的内容

基于证据和图推理的文档级关系抽取方法: 以医学关系为例

Document-Level Relation Extraction Method Based on Evidence and Graph Inference: A Case Study of Medical Relationships

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 34

相关文章 15

编辑推荐

Metrics

本文评价

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于证据和图推理的文档级关系抽取方法: 以医学关系为例

Document-Level Relation Extraction Method Based on Evidence and Graph Inference: A Case Study of Medical Relationships

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 34

相关文章 15

编辑推荐

Metrics

本文评价