RoBFM：双向焦点增强机制的水产病害防治因果关系抽取

曹佩荣; 张思佳; 李政霖; 安宗诗; 张佳琪

doi:10.13300/j.cnki.hnlkxb.2026.03.014

您当前的位置：

首页 >

文章列表页 >

RoBFM：双向焦点增强机制的水产病害防治因果关系抽取

农业人工智能专题 | 更新时间：2026-11-05

- RoBFM：双向焦点增强机制的水产病害防治因果关系抽取
- RoBFM：causal relationship extraction for aquaculture disease prevention and control via a bidirectional focus enhancement mechanism
- 华中农业大学学报 2026年45卷第3期页码：161-172
- 作者机构：
  
  1.大连海洋大学信息工程学院/大连市智慧渔业重点实验室/大连海洋大学设施渔业教育部重点实验室，大连116023
  2.辽宁省海洋信息技术重点实验室，大连116023
- 作者简介：
  
  曹佩荣，E-mail：caopeirong08@163.com
  张思佳，E-mail：zhangsijia@dlou.edu.cn
- 基金信息：
  
  辽宁省重点研发计划项目(2023JH26/10200015)
- DOI：10.13300/j.cnki.hnlkxb.2026.03.014
  中图分类号： TP391.1;S941
- 收稿：2025-06-30，
  
  纸质出版：2026-05-25
- 稿件说明：
移动端阅览
曹佩荣，张思佳，李政霖，等.RoBFM：双向焦点增强机制的水产病害防治因果关系抽取［J］.华中农业大学学报，2026，45（3）：161‐172.

CAO Peirong,ZHANG Sijia,LI Zhenglin,et al.RoBFM：causal relationship extraction for aquaculture disease prevention and control via a bidirectional focus enhancement mechanism[J].Journal of Huazhong Agricultural University,2026,45(03):161-172.
曹佩荣，张思佳，李政霖，等.RoBFM：双向焦点增强机制的水产病害防治因果关系抽取［J］.华中农业大学学报，2026，45（3）：161‐172. DOI： 10.13300/j.cnki.hnlkxb.2026.03.014.

CAO Peirong,ZHANG Sijia,LI Zhenglin,et al.RoBFM：causal relationship extraction for aquaculture disease prevention and control via a bidirectional focus enhancement mechanism[J].Journal of Huazhong Agricultural University,2026,45(03):161-172. DOI： 10.13300/j.cnki.hnlkxb.2026.03.014.

摘要

为提升水产疾病防治中复杂与多层次因果关系抽取的准确性，引入一种双向焦点增强机制（bidirectional focus enhancement mechanism，BFM），提出RoBFM模型（RoBERTa-wwm-ext-large bidirectional focus enhancement mechanism）。该模型结合预训练语言模型RoBERTa-wwm-ext-large生成高质量词嵌入，并利用双向长短时记忆网络（bi-directional long short-term memory，BiLSTM）增强长距离依赖性建模。RoBFM的核心是通过BFM机制的前后向权重分配，强制解耦并聚焦因果语义角色。为全面评估模型性能，在公开数据集DuIE和自建的领域专用数据集DLOU-CRE上开展了基线对比试验与消融实验。试验结果显示，该模型在公开数据集DuIE和自建的领域专用数据集DLOU-CRE上的

值等指标均优于现有模型。尤其在DLOU-CRE数据集上，

值达到了68.23%。结果表明，该方法用于水产病害防治因果关系抽取中具有更好的效果。

Abstract

To enhance the accuracy of extracting complex，multi-level causal relationships in aquatic disease control，this study introduces a bidirectional focus enhancement mechanism （BFM） and proposes the RoBFM model （RoBERTa-wwm-ext-large integrated with bidirectional focus enhancement mechanism）.The model integrates the RoBERTa-wwm-ext-large pre-trained language model to generate high-quality word embeddings and leverages Bi-directional long short-term memory （BiLSTM） networks to strengthen long-distance dependency modeling.The core innovation of RoBFM resides in the BFM mechanism，which employs forward and backward weight allocation to explicitly decouple and focus on causal semantic roles.To systematically evaluate the model’s performance，this paper conducts baseline comparison and ablation experiments on the public dataset DuIE and the self-constructed，domain-specific dataset DLOU-CRE.Experimental results demonstrate that the proposed model surpasses existing baselines in terms of

score and other metrics on both datasets.Notably，the model achieves an

score of 68.23% on the DLOU-CRE dataset，demonstrating that the proposed method is more effective for causal relationship extraction in the prevention and control of aquatic animal diseases.

关键词

Keywords

references

LI Z L，ZHANG S J，ZHANG J Q，et al.AquaMTL-chain：advancing multi-task learning for event extraction in aquaculture［J/OL］.Aquaculture，2026，611：743001［2025-06-30］.https：//doi.org/10.1016/j.aquaculture.2025.743001.

冉紫涵，张仰森，向尕，等.因果关系抽取研究综述［J］.北京信息科技大学学报（自然科学版），2023，38（3）：89-100.RAN Z H，ZHANG Y S，XIANG G，et al.A review of causality extraction studies［J］.Journal of Beijing Information Science & Technology University，2023，38（3）：89-100 （in Chinese with English abstract） .

张思佳，于红.大模型在水产养殖病害防治中的创新应用与展望［J］.大连海洋大学学报，2024，39（3）：369-382.ZHANG S J，YU H.Innovative applications and prospects of large models in disease prevention and control for aquaculture：a review［J］.Journal of Dalian Fisheries University，2024，39（3）：369-382 （in Chinese with English abstract） .

KHOO C S G，KORNFILT J，ODDY R N，et al.Automatic extraction of cause-effect information from newspaper text without knowledge-based inferencing［J］.Literary and linguistic computing，1998，13（4）：177-186.

GIRJU R，MOLDOVAN D.Text mining for causal relations［C］//Proceedings of the 15th International Florida Artificial Intelligence Research Society Conference. Palo Alto： AAAI Press，2002：360-364.

GIRJU R.Automatic detection of causal relations for question answering［C］//Proceedings of the ACL 2003 Workshop on Multilingual Summarization and Question Answering.Sapporo：Japan Association for Computational Linguistics，2003：76-83.

LUO Z Y，SHA Y C，ZHU K Q，et al.Commonsense causal reasoning between short texts［C］//International Conference on Principles of Knowledge Representation and Reasoning.Cape Town，South Africa：Association for the Advancement of Artificial Intelligence （AAAI），2016：421-431.

DE SILVA T N，XIAO Z，ZHAO R，et al.Causal relation identification using convolutional neural networks and knowledge based features［J］.International journal of mechanical and mechatronics engineering，2017，11（6）：703-708.

LI P F，MAO K Z.Knowledge-oriented convolutional neural network for causal relation extraction from natural language texts［J］.Expert systems with applications，2019，115：512-523.

DASGUPTA T，SAHA R，DEY L，et al.Automatic extraction of causal relations from text using linguistically informed deep neural networks［C］//Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue.Melbourne：Australia Association for Computational Linguistics，2018：306-316.

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，volume 1 （long and short papers）. Minneapolis：Association for Computational Linguistics， 2019： 4171-4186.

LIU Y H，OTT M，GOYAL N，et al.RoBERTa：a robustly optimized BERT pretraining approach［PP/OL］.arXiv， 2019 ：1907.11692［2025-06-30］.https：//arxiv.org/abs/1907.11692.

LI Z L，ZHANG S J，AN Z S.Base on ChatGLM extraction of medication events in aquaculture with few samples［J/OL］.Aquaculture international，2025，33（2）：89［2025-06-30］.https：//doi.org/10.1007/s10499-024-01686-y.

YUAN J Y，ZHANG F Y，QIU Y M，et al.Document-level biomedical relation extraction via hierarchical tree graph and relation segmentation module［J/OL］.Bioinformatics，2024，40（7）：btae418［2025-06-30］.https：//doi.org/10.1093/bioinformatics/btae418.

ANUYAH S，VANSCHAIK J，JAIN P，et al.An empirical study of causal relation extraction transfer：design and data［PP/OL］.arXiv，2025：2503.06076［2025-06-30］.https：//arxiv.org/abs/2503.06076.

CUI Y M，CHE W X，LIU T，et al.Pre-training with whole word masking for Chinese BERT［J］.IEEE/ACM transactions on audio，speech，and language processing，2021，29：3504-3514.

GAO W，ZHENG X，ZHAO S.Named entity recognition method of Chinese EMR based on BERT-BiLSTM-CRF［C/OL］//Journal of physics：conference series.IOP Publishing，2021，1848（1）：012083［2025-06-30］.https：//doi：10.1088/1742-6596/1848/1/012083.

ZHAO X，DENG Y，YANG M，et al.A comprehensive survey on relation extraction：recent advances and new frontiers［J］.ACM computing surveys，2024，56（11）：1-39.

HU S，ZHANG H，HU X，et al.Chinese named entity recognition based on BERT-CRF model［C］//2022 IEEE/ACIS 22nd international conference on computer and information science （ICIS）.IEEE，2022：105-108.

LI W，DU Y，LI X，et al.UD_BBC：Named entity recognition in social network combined BERT-BiLSTM-CRF with active learning［J/OL］.Engineering applications of artificial intelligence，2022，116：105460［2025-06-30］.https：//doi.org/10.1016/j.engappai.2022.105460.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

生物质灰添加量对自蔓延合成基质块性能的影响

团头鲂smg9基因SNP位点鉴定及其与抗嗜水气单胞菌感染的关联分析

中药防治猪流行性腹泻的作用机制研究进展

复合菌剂对猪粪水重金属的钝化效果及沙地燕麦的吸收特征

晾制过程中喷施脂氧合酶制剂对改善茄衣烟叶含青的作用研究