{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T07:23:31Z","timestamp":1777706611964,"version":"3.51.4"},"reference-count":32,"publisher":"SAGE Publications","issue":"1","license":[{"start":{"date-parts":[[2024,3,22]],"date-time":"2024-03-22T00:00:00Z","timestamp":1711065600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of Intelligent &amp; Fuzzy Systems: Applications in Engineering and Technology"],"published-print":{"date-parts":[[2025,7]]},"abstract":"<jats:p>Legal judgment prediction(LJP) has achieved remarkable results. However, existing methods still face problems such as difficulties in obtaining key feature words for charges, which impose limitations on the improvement of prediction results. To this end, we propose a legal judgment prediction model with legal feature Word subgraph Label-Embedding and Dual-knowledge Distillation(WLEDD). Compared with traditional methods, our method has two contributions: (1) To mitigate the impact of overly sparse tail class data and high similarity text representations, we capture the critical features related to the charges by fusing LDA and legal feature word subgraphs. Then we encode them as label information to obtain highly distinguished representations of legal documents. (2) To solve the problem of high difficulty in some subtasks in LJP, we perform subtask-oriented compression of models to construct a student model with lower complexity and higher accuracy through dual knowledge distillation. Moreover, we exploit the logical association between the subtasks to constrain the labels of articles by charge prediction results. It greatly reduces the difficulty of article prediction. Experimental results on four datasets show that our approach significantly outperforms the baseline models. Compared with the state-of-art method, the F1 value of WLEDD for charge prediction has increased by an average of 2.57% . For article prediction, the F1 value has increased by an average of 1.09% . In addition, we demonstrate its effectiveness through ablation experiments and analytical experiments.<\/jats:p>","DOI":"10.3233\/jifs-237323","type":"journal-article","created":{"date-parts":[[2024,3,22]],"date-time":"2024-03-22T12:01:11Z","timestamp":1711108871000},"page":"260-272","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["WLEDD: Legal judgment prediction with legal feature word subgraph label-embedding and dual-knowledge distillation"],"prefix":"10.1177","volume":"49","author":[{"given":"Xiao","family":"Wei","sequence":"first","affiliation":[{"name":"School of Computer Engineering and Science, Shanghai University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yidian","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Engineering and Science, Shanghai University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2024,3,22]]},"reference":[{"key":"e_1_3_1_2_1","doi-asserted-by":"crossref","unstructured":"YangW.JiaW.ZhouX.LuoY. Legal judgment prediction via multi-perspective bi-feedback network. CoRR abs\/1905.03969 2019.","DOI":"10.24963\/ijcai.2019\/567"},{"key":"e_1_3_1_3_1","doi-asserted-by":"publisher","unstructured":"DongQ.NiuS. Legal judgment prediction via relational learning. In F. Diaz C. Shah T. Suel P. Castells R. Jones and T. Sakai editors SIGIR (2021) pp. 983\u2013992. ACM. doi:10.1145\/3404835.3462931.","DOI":"10.1145\/3404835.3462931"},{"key":"e_1_3_1_4_1","doi-asserted-by":"publisher","unstructured":"PaulS.GoyalP.GhoshS. Automatic charge identification from facts: A few sentence-level charge annotations is all you need. In D. Scott N. Bel and C. Zong editors COLING (2020) pp. 1011\u20131022. ICCL.10.18653\/v1\/2020.coling-main.88.","DOI":"10.18653\/v1\/2020.coling-main.88"},{"key":"e_1_3_1_5_1","doi-asserted-by":"publisher","unstructured":"ZhongH.ZhouJ.QuW.LongY.GuY. An element-aware multi-representation model for law article prediction. In B. Webber T. Cohn Y. He and Y. Liu editors EMNLP (2020) pp. 6663\u20136668. ACL. doi:10.18653\/v1\/2020.emnlp-main.540.","DOI":"10.18653\/v1\/2020.emnlp-main.540"},{"key":"e_1_3_1_6_1","doi-asserted-by":"publisher","unstructured":"XuN.WangP.ChenL.PanL.WangX.ZhaoJ. Distinguish confusing law articles for legal judgment prediction. In D. Jurafsky J. Chai N. Schluter and J.R. Tetreault editors ACL (2020) pp. 3086\u20133095. ACL. doi:10.18653\/v1\/2020.acl-main.280.","DOI":"10.18653\/v1\/2020.acl-main.280"},{"key":"e_1_3_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2021.102780"},{"key":"e_1_3_1_8_1","unstructured":"HuZ.LiX.TuC.LiuZ.SunM. Few-shot charge prediction with discriminative legal attributes. In Emily M. Bender Leon Derczynski and Pierre Isabelle editors COLING (2018) pp. 487\u2013498. ACL."},{"key":"e_1_3_1_9_1","doi-asserted-by":"crossref","unstructured":"YueL.LiuQ.JinB.WuH.ZhangK.AnY.ChengM.YinB.WuD. Neurjudge: A circumstance-aware neural framework for legal judgment prediction. In F. Diaz C. Shah T. Suel P. Castells R. Jones and T. Sakai editors SIGIR (2021) pp. 973\u2013982 New York NY USA. ACM.","DOI":"10.1145\/3404835.3462826"},{"key":"e_1_3_1_10_1","doi-asserted-by":"publisher","unstructured":"FengY.LiC.NgV. Legal judgment prediction via event extraction with constraints. In S. Muresan P. Nakov and A. Villavicencio editors ACL (2022) pp. 648\u2013664. ACL. doi:10.18653\/v1\/2022.acllong.48.","DOI":"10.18653\/v1\/2022.acllong.48"},{"key":"e_1_3_1_11_1","doi-asserted-by":"publisher","DOI":"10.2307\/1955796"},{"key":"e_1_3_1_12_1","doi-asserted-by":"publisher","DOI":"10.2307\/1190728"},{"key":"e_1_3_1_13_1","doi-asserted-by":"publisher","DOI":"10.2307\/1951767"},{"key":"e_1_3_1_14_1","doi-asserted-by":"crossref","unstructured":"GanL.KuangK.YangY.WuF. Judgment prediction via injecting legal knowledge into neural networks. In AAAI (2021) pp. 12866\u201312874. AAAI Press.","DOI":"10.1609\/aaai.v35i14.17522"},{"key":"e_1_3_1_15_1","doi-asserted-by":"publisher","unstructured":"WangG.LiC.WangW.ZhangY.ShenD.ZhangX.HenaoR.CarinL. Joint embedding of words and labels for text classification. In I. Gurevych and Y. Miyao editors ACL (2018) pp. 2321\u20132331. ACL. doi:10.18653\/v1\/P18-1216.","DOI":"10.18653\/v1\/P18-1216"},{"key":"e_1_3_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.10.099"},{"key":"e_1_3_1_17_1","doi-asserted-by":"publisher","unstructured":"DuC.ChenZ.FengF.ZhuL.GanT.NieL. Explicit interaction model towards text classification In AAAI (2019) pp. 6359\u20136366. AAAI Press. doi:10.1609\/aaai.v33i01.33016359.","DOI":"10.1609\/aaai.v33i01.33016359"},{"key":"e_1_3_1_18_1","unstructured":"ZhangH.XiaoL.ChenW.WangY.JinY. Multitask label embedding for text classification. In E. Riloff D. Chiang J. Hockenmaier and J. Tsujii editors EMNLP (2018) pp. 4545\u20134553. ACL."},{"key":"e_1_3_1_19_1","doi-asserted-by":"publisher","unstructured":"DanJ.LiaoX.XuL.HuW.ZhangT. A joint label-enhanced representation based on pre-trained model for charge prediction. In W. Lu S. Huang Y. Hong and X. Zhou editors NLPCC volume 13551 of Lecture Notes in Computer Science (2022) pp. 694\u2013705. Springer. doi:10.1007\/978-3-031-17120-8_54.","DOI":"10.1007\/978-3-031-17120-8_54"},{"key":"e_1_3_1_20_1","unstructured":"HintonG.E.VinyalsO.DeanJ. Distilling the knowledge in a neural network. CoRR abs\/1503.02531 2015."},{"key":"e_1_3_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.10.083"},{"key":"e_1_3_1_22_1","doi-asserted-by":"crossref","unstructured":"ZhangS.GuoS.WangL.HuangW.ScottM.R. Knowledge integration networks for action recognition. In AAAI (2020) pp. 12862\u201312869. AAAI Press.","DOI":"10.1609\/aaai.v34i07.6983"},{"key":"e_1_3_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2963882"},{"key":"e_1_3_1_24_1","doi-asserted-by":"publisher","unstructured":"PanB.CaiH.HuangD.-A.LeeK.-H.GaidonA.AdeliE.NieblesJ.C. Spatiotemporal graph for video captioning with knowledge distillation. In CVPR (2020) pp. 10867\u201310876. IEEE. doi:10.1109\/CVPR42600.2020.01088.","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"e_1_3_1_25_1","doi-asserted-by":"crossref","unstructured":"AguilarG.LingY.ZhangY.YaoB.FanX.GuoC. Knowledge distillation from internal representations. In AAAI (2020) pp. 7350\u20137357. AAAI.","DOI":"10.1609\/aaai.v34i05.6229"},{"key":"e_1_3_1_26_1","doi-asserted-by":"publisher","unstructured":"SunH.WangR.ChenK.UtiyamaM.SumitaE.ZhaoT. Knowledge distillation for multilingual unsupervised neural machine translation. In D. Jurafsky J. Chai N. Schluter and J.R. Tetreault editors ACL (2020) pp. 3525\u20133535. ACL. doi:10.18653\/v1\/2020.acl-main.324.","DOI":"10.18653\/v1\/2020.acl-main.324"},{"key":"e_1_3_1_27_1","doi-asserted-by":"publisher","unstructured":"WangF.YanJ.MengF.ZhouJ. Selective knowledge distillation for neural machine translation. In C. Zong F. Xia W. Li and R. Navigli editors IJCNLP (2021) pp. 6456\u20136466. ACL. doi:10.18653\/v1\/2021.acl-long.504.","DOI":"10.18653\/v1\/2021.acl-long.504"},{"key":"e_1_3_1_28_1","doi-asserted-by":"publisher","unstructured":"ZhouW.XuC.McAuleyJ.J. BERT learns to teach: Knowledge distillation with meta learning. In S. Muresan P. Nakov and A. Villavicencio editors ACL (2022) pp. 7037\u20137049. ACL. doi:10.18653\/v1\/2022.acl-long.485.","DOI":"10.18653\/v1\/2022.acl-long.485"},{"key":"e_1_3_1_29_1","doi-asserted-by":"publisher","unstructured":"LuL.GuoM.RenalsS. Knowledge distillation for small-footprint highway networks. In ICASSP (2017) pp. 4820\u20134824. IEEE. doi:10.1109\/ICASSP.2017.7953072.","DOI":"10.1109\/ICASSP.2017.7953072"},{"key":"e_1_3_1_30_1","doi-asserted-by":"publisher","unstructured":"Andres Perez F.Sanguineti V.MorerioP.Murino V. Audio-visual model distillation using acoustic images. In WACV (2020) pp. 2843\u20132852. IEEE. doi:10.1109\/WACV45572.2020.9093307.","DOI":"10.1109\/WACV45572.2020.9093307"},{"key":"e_1_3_1_31_1","doi-asserted-by":"publisher","unstructured":"MingoteV.MiguelA.RibasD.GimenezA.O.LleidaE. Knowledge distillation and random erasing data augmentation for text-dependent speaker verification. In ICASSP (2020) pp. 6824\u20136828. IEEE. doi:10.1109\/ICASSP40776.2020.9053153.","DOI":"10.1109\/ICASSP40776.2020.9053153"},{"key":"e_1_3_1_32_1","unstructured":"XiaoC.ZhongH.GuoZ.TuC.LiuZ.SunM.FengY.HanX.HuZ.WangH.XuJ. CAIL2018: A large-scale legal dataset for judgment prediction. CoRR abs\/1807.02478 2018."},{"key":"e_1_3_1_33_1","unstructured":"ZhongH.XiaoC.GuoZ.TuC.LiuZ.SunM.FengY.HanX.HuZ.WangH.XuJ. Overview of CAIL2018: Legal judgment prediction competition. CoRR abs\/1810.05851 2018."}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems: Applications in Engineering and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-237323","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.3233\/JIFS-237323","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-237323","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:47:20Z","timestamp":1777456040000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.3233\/JIFS-237323"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,22]]},"references-count":32,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["10.3233\/JIFS-237323"],"URL":"https:\/\/doi.org\/10.3233\/jifs-237323","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,22]]}}}