{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T22:47:24Z","timestamp":1782946044430,"version":"3.54.5"},"reference-count":57,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2023,10,30]],"date-time":"2023-10-30T00:00:00Z","timestamp":1698624000000},"content-version":"vor","delay-in-days":302,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21A20491"],"award-info":[{"award-number":["U21A20491"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1936109"],"award-info":[{"award-number":["U1936109"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1908214"],"award-info":[{"award-number":["U1908214"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Intelligent Systems"],"published-print":{"date-parts":[[2023,1]]},"abstract":"<jats:p>In general knowledge base question answering (KBQA) models, subject recognition (SR) is usually a precondition of finding an answer, and it is a common way to employ a general named entity recognition (NER) model such as BERT\u2010CRF to recognize the subject. However, in previous researches, the difference between a NER task and a SR task is usually ignored, and a wrong entity recognized by the NER model will certainly lead to a wrong answer in the KBQA task, which is one bottleneck for KBQA performance. In this paper, a multigranularity pruning model (MGPM) is proposed to answer a question when general models fail to recognize a subject. In MGPM, the set of all possible subjects in the Knowledge Base (KB) is pruned by 4 multigranularity pruning submodels successively based on the constraint of relation (domain and tuple), string similarity, and semantic similarity. Experimental results show that our model is compatible with various KBQA models for both single\u2010relation and complex questions answering. The integrated MGPM model (with the BERT\u2010CRF model) achieves a SR accuracy of 94.4% on the SimpleQuestions dataset, 68.6% on the WebQuestionsSP dataset, and 63.7% on the WebQuestions dataset, which outperforms the original model by a margin of 3.6%, 8.6%, and 5.3%, respectively.<\/jats:p>","DOI":"10.1155\/2023\/1202315","type":"journal-article","created":{"date-parts":[[2023,10,30]],"date-time":"2023-10-30T20:20:38Z","timestamp":1698697238000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multigranularity Pruning Model for Subject Recognition Task under Knowledge Base Question Answering When General Models Fail"],"prefix":"10.1155","volume":"2023","author":[{"given":"Ziming","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7558-3031","authenticated-orcid":false,"given":"Xirong","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoying","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haochen","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8497-611X","authenticated-orcid":false,"given":"Xiaopeng","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Degen","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2023,10,30]]},"reference":[{"key":"e_1_2_10_1_2","doi-asserted-by":"crossref","unstructured":"DaiZ. LiL. andXuW. Cfo: conditional focused neural question answering with large-scale knowledge bases Proceedings of the Annual Meeting of the Association for Computational Linguistics August 2016 Berlin Germany 800\u2013810.","DOI":"10.18653\/v1\/P16-1076"},{"key":"e_1_2_10_2_2","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00127"},{"key":"e_1_2_10_3_2","doi-asserted-by":"crossref","unstructured":"BollackerK. EvansC. ParitoshP. Tim Sturge andTaylorJ. Freebase: a collaboratively created graph database for structuring human knowledge Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data June 2008 Vancouver Canada 1247\u20131250.","DOI":"10.1145\/1376616.1376746"},{"key":"e_1_2_10_4_2","doi-asserted-by":"crossref","unstructured":"YaoX.andVan DurmeB. Information extraction over structured data: question answering with freebase Proceedings of the Annual Meeting of the Association for Computational Linguistics June 2014 Baltimore Maryland 956\u2013966.","DOI":"10.3115\/v1\/P14-1090"},{"key":"e_1_2_10_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2019.2909826"},{"key":"e_1_2_10_6_2","unstructured":"QuY. LiuJ. KangL. ShiQ. andYeD. Question answering over freebase via attentive rnn with similarity matrix based cnn 2018 https:\/\/arxiv.org\/abs\/1804.03317."},{"key":"e_1_2_10_7_2","doi-asserted-by":"crossref","unstructured":"ZhaoW. ChungT. GoyalA. andMetallinouA. Simple question answering with subgraph ranking and joint-scoring 2019 https:\/\/arxiv.org\/abs\/1904.04049.","DOI":"10.18653\/v1\/N19-1029"},{"key":"e_1_2_10_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2019.2918675"},{"key":"e_1_2_10_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2019.2904337"},{"key":"e_1_2_10_10_2","unstructured":"DevlinJ. ChangM.-W. LeeK. andToutanovaK. Bert: pre-training of deep bidirectional transformers for language understanding Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies June 2019 Minneapolis Minnesota 4171\u20134186."},{"key":"e_1_2_10_11_2","unstructured":"LanZ. ChenM. GoodmanS. GimpelK. SharmaP. andRaduS. Albert: a lite bert for self-supervised learning of language representations 2019 https:\/\/arxiv.org\/abs\/1909.11942."},{"key":"e_1_2_10_12_2","first-page":"5754","volume-title":"Proceedings of the 2019 Annual Conference on Neural Information Processing Systems","author":"Yang Z.","year":"2019"},{"key":"e_1_2_10_13_2","unstructured":"ClarkK. LuongM.-T. QuocV. L. andManningC. D. Electra: pre-training text encoders as discriminators rather than generators Proceedings of the International Conference on Learning Representations June 2020 Addis Ababa Ethiopia."},{"key":"e_1_2_10_14_2","doi-asserted-by":"publisher","DOI":"10.1017\/s1351324921000127"},{"key":"e_1_2_10_15_2","doi-asserted-by":"publisher","DOI":"10.1017\/s1351324921000139"},{"key":"e_1_2_10_16_2","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00462"},{"key":"e_1_2_10_17_2","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00434"},{"key":"e_1_2_10_18_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.semeval-1.175"},{"key":"e_1_2_10_19_2","doi-asserted-by":"crossref","unstructured":"LuoD. SuJ. andYuS. A bert-based approach with relation-aware attention for knowledge base question answering Proceedings of the International Joint Conference on Neural Networks July 2020 Glasgow UK 1\u20138.","DOI":"10.1109\/IJCNN48605.2020.9207186"},{"key":"e_1_2_10_20_2","doi-asserted-by":"crossref","unstructured":"ZhuW. Autorc: improving bert based relation classification models via architecture search Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Student Research Workshop June 2021 Toronto Canada 33\u201343.","DOI":"10.18653\/v1\/2021.acl-srw.4"},{"key":"e_1_2_10_21_2","doi-asserted-by":"crossref","unstructured":"WangA. SinghA. JulianM. HillF. LevyO. SamuelR. andGlueB. A multi-task benchmark and analysis platform for natural language understanding Proceedings of the 7th International Conference on Learning Representations November 2019 Brussels Belgium.","DOI":"10.18653\/v1\/W18-5446"},{"key":"e_1_2_10_22_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00104"},{"key":"e_1_2_10_23_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00334"},{"key":"e_1_2_10_24_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00386"},{"key":"e_1_2_10_25_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00429"},{"key":"e_1_2_10_26_2","doi-asserted-by":"publisher","DOI":"10.3390\/app132011249"},{"key":"e_1_2_10_27_2","doi-asserted-by":"crossref","unstructured":"YanH. GuiT. DaiJ. GuoQ. ZhangZ. andQiuX. A unified generative framework for various ner subtasks Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics August 2021 Bangkok Thailand 5808\u20135822.","DOI":"10.18653\/v1\/2021.acl-long.451"},{"key":"e_1_2_10_28_2","doi-asserted-by":"crossref","unstructured":"LiF. WangZ. HuiS. C. LiaoL. SongD. XuJ. HeG. andJiaM. Modularized interaction network for named entity recognition Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing August 2021 Toronto Canada 200\u2013209.","DOI":"10.18653\/v1\/2021.acl-long.17"},{"key":"e_1_2_10_29_2","doi-asserted-by":"crossref","unstructured":"WangY. YuB. ZhuH. LiuT. NanY. andSunL. Discontinuous named entity recognition as maximal clique discovery Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing August 2021 Toronto Canada 764\u2013774.","DOI":"10.18653\/v1\/2021.acl-long.63"},{"key":"e_1_2_10_30_2","unstructured":"SuW. ZhuX. CaoY. LiB. LuL. WeiF. andDaiJ. Vl-bert: pre-training of generic visual-linguistic representations Proceedings of the International Conference on Learning Representations January 2020 Addis Ababa Ethiopia."},{"key":"e_1_2_10_31_2","doi-asserted-by":"crossref","unstructured":"TanH.andBansalM. Lxmert: learning cross-modality encoder representations from transformers Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing November 2019 Hong Kong China 5100\u20135111.","DOI":"10.18653\/v1\/D19-1514"},{"key":"e_1_2_10_32_2","doi-asserted-by":"crossref","unstructured":"SunC. MyersA. VondrickC. MurphyK. andSchmidC. Videobert: a joint model for video and language representation learning Proceedings of the 2019 IEEE\/CVF International Conference on Computer Vision October 2019 Seoul Korea (South) 7463\u20137472.","DOI":"10.1109\/ICCV.2019.00756"},{"key":"e_1_2_10_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"e_1_2_10_34_2","doi-asserted-by":"crossref","unstructured":"SchneiderS. BaevskiA. CollobertR. andAuliM. wav2vec: unsupervised pre-training for speech recognition Proceedings of the 20th Annual Conference of the International Speech Communication Association September 2019 Hong Kong China 3465\u20133469.","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"e_1_2_10_35_2","doi-asserted-by":"crossref","unstructured":"ChuangY.-S. LiuC.-L. andLeeH. Y. Speechbert: An audio-and-text jointly learned language model for end-to-end spoken question answering Proceedings of the 21st Annual Conference of the International Speech Communication Association October 2020 Shanghai China 4168\u20134172.","DOI":"10.21437\/Interspeech.2020-1570"},{"key":"e_1_2_10_36_2","doi-asserted-by":"crossref","unstructured":"YangJ. GuptaA. UpadhyayS. HeL. GoelR. andPaulS. Tableformer: robust transformer modeling for table-text encoding Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics May 2022 Dublin Ireland 528\u2013537.","DOI":"10.18653\/v1\/2022.acl-long.40"},{"key":"e_1_2_10_37_2","doi-asserted-by":"crossref","unstructured":"SuH. ShiW. ShenX. ZhouX. JiT. FangJ. andZhouJ. Rocbert: robust Chinese bert with multimodal contrastive pretraining Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics May 2022 Dublin Ireland 921\u2013931.","DOI":"10.18653\/v1\/2022.acl-long.65"},{"key":"e_1_2_10_38_2","doi-asserted-by":"crossref","unstructured":"LiuS. LiK. andLiZ. A robustly optimized bmrc for aspect sentiment triplet extraction Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies July 2022 Seattle WA USA 272\u2013278.","DOI":"10.18653\/v1\/2022.naacl-main.20"},{"key":"e_1_2_10_39_2","doi-asserted-by":"crossref","unstructured":"ZhuD.andMichaelA. Is bert robust to label noise? a study on learning with noisy labels in text classification Proceedings of the Third Workshop on Insights from Negative Results in NLP May 2022 Dublin Ireland 62\u201367.","DOI":"10.18653\/v1\/2022.insights-1.8"},{"key":"e_1_2_10_40_2","doi-asserted-by":"crossref","unstructured":"YeF. YueF. andYilmazE. Assist: towards label noise-robust dialogue state tracking Proceedings of the Findings of the Association for Computational Linguistics: ACL 2022 May 2022 London UK 2719\u20132731.","DOI":"10.18653\/v1\/2022.findings-acl.214"},{"key":"e_1_2_10_41_2","doi-asserted-by":"crossref","unstructured":"NguyenH.andKhatwaniD. Robust product classification with instance-dependent noise Proceedings of the Fifth Workshop on E-Commerce and NLP May 2022 London UK 171\u2013180.","DOI":"10.18653\/v1\/2022.ecnlp-1.20"},{"key":"e_1_2_10_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2023.3252608"},{"key":"e_1_2_10_43_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00470"},{"key":"e_1_2_10_44_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00336"},{"key":"e_1_2_10_45_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00282"},{"key":"e_1_2_10_46_2","doi-asserted-by":"crossref","unstructured":"LiuK. FuY. TanC. ChenM. ZhangN. HuangS. andGaoS. Noisy-labeled ner with confidence estimation Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies May 2021 Hong Kong China 3437\u20133445.","DOI":"10.18653\/v1\/2021.naacl-main.269"},{"key":"e_1_2_10_47_2","first-page":"845","article-title":"Binary codes capable of correcting deletions, insertions and reversals","volume":"163","author":"Levenshtein V. I.","year":"1966","journal-title":"Doklady Akademii Nauk SSSR"},{"key":"e_1_2_10_48_2","unstructured":"AntoineB. UsunierN. ChopraS. andWestonJ. Large-scale simple question answering with memory networks 2015 https:\/\/arxiv.org\/abs\/1506.02075."},{"key":"e_1_2_10_49_2","unstructured":"WenY. RichardsonM. MeekC. andChangM. W. The value of semantic parse labeling for knowledge base question answering Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics August 2016 Berlin Germany 201\u2013206."},{"key":"e_1_2_10_50_2","doi-asserted-by":"crossref","unstructured":"BerantJ. ChouA. RoyF. andLiangP. Semantic parsing on freebase from question-answer pairs Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing October 2013 Seattle WA USA 1533\u20131544.","DOI":"10.18653\/v1\/D13-1160"},{"key":"e_1_2_10_51_2","unstructured":"KingmaD.andJimmyB. Adam: a method for stochastic optimization 2015 https:\/\/arxiv.org\/abs\/1412.6980."},{"key":"e_1_2_10_52_2","unstructured":"SuJ. AhmedM. PanS. HouJ. SunJ. HuangW. WenB. andLiuY. Global pointer: novel efficient span-based approach for named entity recognition 2022 https:\/\/arxiv.org\/abs\/2208.03054."},{"key":"e_1_2_10_53_2","doi-asserted-by":"crossref","unstructured":"RazzhigaevA. SalnikovM. MalykhV. BraslavskiP. andPanchenkoA. A system for answering simple questions in multiple languages Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics July 2023 Toronto Canada 524\u2013537.","DOI":"10.18653\/v1\/2023.acl-demo.51"},{"key":"e_1_2_10_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2017.2773081"},{"key":"e_1_2_10_55_2","doi-asserted-by":"crossref","unstructured":"PetrochukM.andZettlemoyerL. Simplequestions nearly solved: a new upperbound and baseline approach Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing October 2018 Brussels Belgium 554\u2013558.","DOI":"10.18653\/v1\/D18-1051"},{"key":"e_1_2_10_56_2","doi-asserted-by":"crossref","unstructured":"HuangX. ZhangJ. LiD. andLiP. Knowledge graph embedding based questiosn answering Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining October 2019 Melbourne VIC Australia 105\u2013113.","DOI":"10.1145\/3289600.3290956"},{"key":"e_1_2_10_57_2","doi-asserted-by":"crossref","unstructured":"WangZ. XuX. LiX. SongX. WeiX. andHuangD. Ssmfrp: semantic similarity model for relation prediction in kbqa based on pre-trained models Proceedings of the 2022 International Conference on Artificial Neural Networks September 2022 Bristol UK 294\u2013306.","DOI":"10.1007\/978-3-031-15931-2_25"}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/ijis\/2023\/1202315.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/ijis\/2023\/1202315.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2023\/1202315","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T05:20:40Z","timestamp":1735622440000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2023\/1202315"}},"subtitle":[],"editor":[{"given":"Mohammad R.","family":"Khosravi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2023,1]]},"references-count":57,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,1]]}},"alternative-id":["10.1155\/2023\/1202315"],"URL":"https:\/\/doi.org\/10.1155\/2023\/1202315","archive":["Portico"],"relation":{},"ISSN":["0884-8173","1098-111X"],"issn-type":[{"value":"0884-8173","type":"print"},{"value":"1098-111X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1]]},"assertion":[{"value":"2023-03-03","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-10-19","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-10-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"1202315"}}