基于潜在关系的实体关系联合抽取模型

doi:10.3778/j.issn.1673-9418.2301061

摘要/Abstract

摘要： 实体关系联合抽取的作用是从特定文本中识别出实体和对应关系，同时它也是知识图谱构建和更新的基础。目前的联合抽取方法在追求性能的同时都忽略了抽取过程中的信息冗余。针对此问题，提出基于潜在关系的实体关系联合抽取模型，通过设计一种新的解码方式来减少预测过程中关系、实体和三元组的冗余信息，从整体上分为提取潜在实体对、解码关系两步来完成从句子中抽取三元组的任务。首先通过潜在实体对提取器预测实体间是否存在潜在关系，同时筛选出置信度高的实体对作为最终的潜在实体对；其次将关系解码视作多标签二分类任务，通过关系解码器预测每个潜在实体对之间全部关系的置信度；最后通过置信度确定关系数量和类型，以完成三元组的抽取任务。在两个通用数据集上的实验结果表明，所提模型相比基线模型在准确率和[F1]指标上的效果更好，验证了所提模型的有效性，消融实验也证明了模型内部各部分的有效性。

关键词: 实体关系联合抽取, 潜在关系, 潜在实体对, 多标签二分类任务, 信息冗余

Abstract: The role of joint entity and relation extraction is to identify entities and their corresponding relations from specific texts, and it is also the basis for constructing and updating knowledge graph. Currently, joint extraction methods ignore information redundancy in the extraction process while pursuing performance. To address this issue, a model based on latent relations for joint entity and relation extraction is proposed. This paper designs a new decoding method to reduce the redundant information of relationships, entities and triples in the prediction process, and it is divided into two steps: extracting potential entity pairs and decoding relationships to complete the extraction of triples. Firstly, the potential entity pair extractor is used to predict whether there is potential relationship between entities, and at the same time, the entity pairs with high confidence are selected as the final potential entity pairs. Secondly, the relational decoding is regarded as a multi-label binary classification task, and the confidence of all relationships between each potential entity pair is predicted by the relational decoder. Finally, the number and type of relationships are determined by confidence to complete the task of extracting triples. Experimental results on two general datasets show that the proposed model is better than the baseline models in terms of accuracy and F1 indicators, which verifies the effectiveness of the proposed model. The ablation experiment also proves the effectiveness of the internal parts of the model.

Key words: joint entity and relation extraction, potential relationship, potential entity pairs, multi-label binary classification tasks, information redundancy

彭晏飞, 张睿思, 王瑞华, 郭家隆. 基于潜在关系的实体关系联合抽取模型[J]. 计算机科学与探索, 2024, 18(4): 1047-1056.

PENG Yanfei, ZHANG Ruisi, WANG Ruihua, GUO Jialong. Potential Relationship Based Joint Entity and Relation Extraction[J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(4): 1047-1056.

参考文献

[1] 李冬梅, 罗斯斯, 张小平, 等. 命名实体识别方法研究综述[J]. 计算机科学与探索, 2022, 16(9): 1954-1968.
LI D M, LUO S S, ZHANG X P, et al. Review on named entity recognition[J]. Journal of Frontiers of Computer Science and Technology, 2022, 16(9): 1954-1968.
[2] JI S, PAN S, CAMBRIA E, et al. A survey on knowledge graphs: representation, acquisition and applications[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33(2): 494-514.
[3] 张少伟, 王鑫, 陈子睿, 等. 有监督实体关系联合抽取方法研究综述[J]. 计算机科学与探索, 2022, 16(4): 713-733.
ZHANG S W, WANG X, CHEN Z R, et al. Survey of supervised joint entity relation extraction methods[J]. Journal of Frontiers of Computer Science and Technology, 2022, 16(4): 713-733.
[4] SOUSA D F, COUTO F M. K-RET: knowledgeable biomedical relation extraction system[J]. Bioinformatics, 2023, 39(4).
[5] KE J, WANG W, CHEN X, et al. Medical entity recognition and knowledge map relationship analysis of Chinese EMRs based on improved BiLSTM-CRF[J]. Computers and Electrical Engineering, 2023, 108: 108709.
[6] KANG H, XIAO J, ZHANG Y, et al. A research toward Chinese named entity recognition based on transfer learning[J]. International Journal of Computational Intelligence Systems, 2023, 16(1): 56.
[7] CEN Y, ZHANG J, WANG G, et al. Trust relationship prediction in Alibaba E-commerce platform[J]. IEEE Transactions on Knowledge and Data Engineering, 2019, 32(5): 1024-1035.
[8] 李宏宇, 段利国, 候晨蕾, 等. 基于CWHC-AM的实体及关系联合抽取方法[J]. 中文信息学报, 2022, 36(11): 79-90.
LI H Y, DUAN L G, HOU C L, et al. Joint extraction of entities and relations based on CWHC-AM[J]. Journal of Chinese Information Processing, 2022, 36(11): 79-90.
[9] PANG Y L, QIN X H, ZHANG Z C. Specific relation attention-guided graph neural networks for joint entity and relation extraction in Chinese EMR[J]. Applied Sciences, 2022, 12(17): 8493.
[10] 彭晏飞, 王瑞华, 张睿思. 基于双集合预测网络的实体关系联合抽取模型[J]. 计算机科学与探索, 2023, 17(7): 1690-1699.
PENG Y F, WANG R H, ZHANG R S. Dual set prediction networks based joint extraction of entity and relation[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(7): 1690-1699.
[11] KANG H, LI X, JIN L, et al. TSPNet: translation supervised prototype network via residual learning for multimodal social relation extraction[J]. Neurocomputing, 2022, 507: 166-179.
[12] TANG G, LI P, HE Y, et al. Latent graph learning with dual-channel attention for relation extraction[J]. Knowledge-Based Systems, 2022, 252: 109471.
[13] ZHAO Q, XU D, LI J, et al. Knowledge guided distance supervision for biomedical relation extraction in Chinese electronic medical records[J]. Expert Systems with Applications, 2022, 204: 117606.
[14] CHAN Y S, ROTH D. Exploiting syntactico-semantic structures for relation extraction[C]//Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Portland, Jun 19-24, 2011. Stroudsburg: ACL, 2011: 551-560.
[15] MIWA M, BANSAL M. End-to-end relation extraction using LSTMs on sequences and tree structures[C]//Procee- dings of the 54th Annual Meeting of the Association for Computational Linguistics, Berlin, Aug 7-12, 2016. Stroudsburg: ACL, 2016: 1105-1116.
[16] GUPTA P, SCHüTZE H, ANDRASSY B. Table filling multi-task recurrent neural network for joint entity and relation extraction[C]//Proceedings of the 26th International Conference on Computational Linguistics, Osaka, Dec 11-17, 2016. New York: ACM, 2016: 2537-2547.
[17] ZENG X, ZENG D, HE S, et al. Extracting relational facts by an end-to-end neural model with copy mechanism[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, Melbourne, Jul 15-20, 2018. Stroudsburg: ACL, 2018: 506-514.
[18] SUI D, CHEN Y, LIU K, et al. Joint entity and relation extraction with set prediction networks[J]. arXiv:2011.01675v1, 2020.
[19] ZHENG S, WANG F, BAO H, et al. Joint extraction of entities and relations based on a novel tagging scheme[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, Vancouver, Jul 30-Aug 4, 2017. Stroudsburg: ACL, 2017: 1227-1236.
[20] DAI D, XIAO X, LYU Y, et al. Joint extraction of entities and overlapping relations using position-attentive sequence labeling[C]//Proceedings of the 2019 AAAI Conference on Artificial Intelligence, Honolulu, Jan 27-Feb 1, 2019. Menlo Park: AAAI, 2019: 6300-6308.
[21] HUANG H, MAO J, LU W, et al. DEASeq2Seq: an attention based sequence to sequence model for short-term metro passenger flow prediction within decomposition -ensemble strategy[J]. Transportation Research Part C: Emerging Technologies, 2023, 146: 103965.
[22] ZHENG H, WEN R, CHEN X, et al. PRGC: potential relation and global correspondence based joint relatio nal triple extraction[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics, Aug 1-6, 2021. Stroudsburg: ACL, 2021: 6225-6235.
[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 Linguistic, Minneapolis, Jun 3-5, 2019. Stroudsburg: ACL, 2019: 4171-4186.
[24] WEI Z, SU J, WANG Y, et al. A novel cascade binary tagging framework for relational triple extraction[C]//Proceedings of the 58th Annual Meeting of the Association for Computa-tional Linguistics, Washington, Jul 6-11, 2020. Stroudsburg: ACL, 2020: 1476-1488.
[25] BEKOULIS G, DELEU J, DEMEESTER T, et al. Joint entity recognition and relation extraction as a multi-head selection problem[J]. Expert Systems with Applications, 2018, 114: 34-45.
[26] ZENG D, ZHANG H, LIU Q. CopyMTL: copy mechanism for joint extraction of entities and relations with multi-task learning[C]//Proceedings of the 2020 AAAI Conference on Artificial Intelligence, New York, Feb 7-20, 2020. Menlo Park: AAAI, 2020: 9507-9514.
[27] WANG Y, YU B, ZHANG Y, et al. TPLinker: single-stage joint extraction of entities and relations through token pair linking[C]//Proceedings of the 28th International Conference on Computational Linguistics, Barcelona, Dec 8-13, 2020. New York: ACM, 2020: 1572-1582.
[28] RIEDEL S, YAO L, MCCALLUM A. Modeling relations and their mentions without labeled text[C]//Proceedings of the 2010 Joint European Conference on Machine Learning and Knowledge Discovery in Databases, Barclona, Sep 20-24, 2010. Berlin, Heidelberg: Springer, 2010: 148-163.
[29] ZHANG F, ZHANG M, LIU S, et al. Enhancing RDF verbalization with descriptive and relational knowledge[J]. ACM Transactions on Asian and Low-Resource Language Information Processing, 2023, 22(6): 1-18.
[30] SENTHILKUMAR N, MANIMEGALAI M, KARPAKAM S, et al. Human action recognition based on spatial-temporal relational model and LSTM-CNN framework[J]. Materials Today: Proceedings, 2022, 57: 2087-2091.