{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T21:24:14Z","timestamp":1787606654731,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":60,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,4,30]],"date-time":"2023-04-30T00:00:00Z","timestamp":1682812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSF MMLI","award":["2019897"],"award-info":[{"award-number":["2019897"]}]},{"name":"DARPA KAIROS","award":["FA8750-19-2-1004"],"award-info":[{"award-number":["FA8750-19-2-1004"]}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["IIS-19-56151"],"award-info":[{"award-number":["IIS-19-56151"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NSF I-GUIDE","award":["2118329"],"award-info":[{"award-number":["2118329"]}]},{"name":"DARPA INCAS","award":["HR001121C0165"],"award-info":[{"award-number":["HR001121C0165"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,4,30]]},"DOI":"10.1145\/3543507.3583354","type":"proceedings-article","created":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T23:30:51Z","timestamp":1682551851000},"page":"1626-1637","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["The Effect of Metadata on Scientific Literature Tagging: A Cross-Field Cross-Model Study"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0540-6758","authenticated-orcid":false,"given":"Yu","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1295-2829","authenticated-orcid":false,"given":"Bowen","family":"Jin","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0129-8542","authenticated-orcid":false,"given":"Qi","family":"Zhu","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2554-2888","authenticated-orcid":false,"given":"Yu","family":"Meng","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3629-2696","authenticated-orcid":false,"given":"Jiawei","family":"Han","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,4,30]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"crossref","unstructured":"Waleed Ammar Dirk Groeneveld Chandra Bhagavatula Iz Beltagy Miles Crawford Doug Downey Jason Dunkelberger Ahmed Elgohary Sergey Feldman Vu Ha 2018. Construction of the Literature Graph in Semantic Scholar. In NAACL-HLT\u201918. 84\u201391.","DOI":"10.18653\/v1\/N18-3011"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018741"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"crossref","unstructured":"Iz Beltagy Kyle Lo and Arman Cohan. 2019. SciBERT: A Pretrained Language Model for Scientific Text. In EMNLP\u201919. 3615\u20133620.","DOI":"10.18653\/v1\/D19-1371"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"crossref","unstructured":"Wei-Cheng Chang Hsiang-Fu Yu Kai Zhong Yiming Yang and Inderjit\u00a0S Dhillon. 2020. Taming pretrained transformers for extreme multi-label text classification. In KDD\u201920. 3163\u20133171.","DOI":"10.1145\/3394486.3403368"},{"key":"e_1_3_2_2_5_1","volume-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv:1412.3555","author":"Chung Junyoung","year":"2014","unstructured":"Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, and Yoshua Bengio. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv:1412.3555 (2014)."},{"key":"e_1_3_2_2_6_1","volume-title":"SPECTER: Document-level Representation Learning using Citation-informed Transformers. In ACL\u201920. 2270\u20132282.","author":"Cohan Arman","year":"2020","unstructured":"Arman Cohan, Sergey Feldman, Iz Beltagy, Doug Downey, and Daniel\u00a0S Weld. 2020. SPECTER: Document-level Representation Learning using Citation-informed Transformers. In ACL\u201920. 2270\u20132282."},{"key":"e_1_3_2_2_7_1","first-page":"317","article-title":"Medical subject headings used to search the biomedical literature","volume":"8","author":"Coletti H","year":"2001","unstructured":"Margaret\u00a0H Coletti and Howard\u00a0L Bleich. 2001. Medical subject headings used to search the biomedical literature. JAMIA 8, 4 (2001), 317\u2013323.","journal-title":"JAMIA"},{"key":"e_1_3_2_2_8_1","volume-title":"Deepxml: A deep extreme multi-label learning framework applied to short text documents. In WSDM\u201921. 31\u201339.","author":"Dahiya Kunal","year":"2021","unstructured":"Kunal Dahiya, Deepak Saini, Anshul Mittal, Ankush Shaw, Kushal Dave, Akshay Soni, Himanshu Jain, Sumeet Agarwal, and Manik Varma. 2021. Deepxml: A deep extreme multi-label learning framework applied to short text documents. In WSDM\u201921. 31\u201339."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz756"},{"key":"e_1_3_2_2_10_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT\u201919. 4171\u20134186.","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT\u201919. 4171\u20134186."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"crossref","unstructured":"Yuxiao Dong Nitesh\u00a0V Chawla and Ananthram Swami. 2017. metapath2vec: Scalable representation learning for heterogeneous networks. In KDD\u201917. 135\u2013144.","DOI":"10.1145\/3097983.3098036"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"crossref","unstructured":"Yuxiao Dong Hao Ma Zhihong Shen and Kuansan Wang. 2017. A century of science: Globalization of scientific collaborations citations and innovations. In KDD\u201917. 1437\u20131446.","DOI":"10.1145\/3097983.3098016"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0507655102"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"crossref","unstructured":"Ziniu Hu Yuxiao Dong Kuansan Wang and Yizhou Sun. 2020. Heterogeneous graph transformer. In WWW\u201920. 2704\u20132710.","DOI":"10.1145\/3366423.3380027"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290979"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"crossref","unstructured":"Himanshu Jain Yashoteja Prabhu and Manik Varma. 2016. Extreme multi-label loss functions for recommendation tagging ranking & other missing label applications. In KDD\u201916. 935\u2013944.","DOI":"10.1145\/2939672.2939756"},{"key":"e_1_3_2_2_17_1","volume-title":"Lightxml: Transformer with dynamic negative sampling for high-performance extreme multi-label text classification. In AAAI\u201921. 7987\u20137994.","author":"Jiang Ting","year":"2021","unstructured":"Ting Jiang, Deqing Wang, Leilei Sun, Huayi Yang, Zhengyang Zhao, and Fuzhen Zhuang. 2021. Lightxml: Transformer with dynamic negative sampling for high-performance extreme multi-label text classification. In AAAI\u201921. 7987\u20137994."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-25712-2"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-020-05888-2"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"crossref","unstructured":"Jingzhou Liu Wei-Cheng Chang Yuexin Wu and Yiming Yang. 2017. Deep learning for extreme multi-label text classification. In SIGIR\u201917. 115\u2013124.","DOI":"10.1145\/3077136.3080834"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btv237"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3119334"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"crossref","unstructured":"Xiao Liu Da Yin Jingnan Zheng Xingjian Zhang Peng Zhang Hongxia Yang Yuxiao Dong and Jie Tang. 2022. OAG-BERT: Towards a Unified Backbone Language Model for Academic Knowledge Services. In KDD\u201922. 3418\u20133428.","DOI":"10.1145\/3534678.3539210"},{"key":"e_1_3_2_2_25_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_2_26_1","volume-title":"PubMed and beyond: a survey of web tools for searching biomedical literature. Database 2011","author":"Zhiyong Lu.","year":"2011","unstructured":"Zhiyong Lu. 2011. PubMed and beyond: a survey of web tools for searching biomedical literature. Database 2011 (2011)."},{"key":"e_1_3_2_2_27_1","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van\u00a0der Maaten Laurens","year":"2008","unstructured":"Laurens van\u00a0der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. JMLR 9 (2008), 2579\u20132605.","journal-title":"JMLR"},{"key":"e_1_3_2_2_28_1","volume-title":"META: Metadata-Empowered Weak Supervision for Text Classification. In EMNLP\u201920. 8351\u20138361.","author":"Mekala Dheeraj","year":"2020","unstructured":"Dheeraj Mekala, Xinyang Zhang, and Jingbo Shang. 2020. META: Metadata-Empowered Weak Supervision for Text Classification. In EMNLP\u201920. 8351\u20138361."},{"key":"e_1_3_2_2_29_1","volume-title":"Decaf: Deep extreme classification with label features. In WSDM\u201921. 49\u201357.","author":"Mittal Anshul","year":"2021","unstructured":"Anshul Mittal, Kunal Dahiya, Sheshansh Agrawal, Deepak Saini, Sumeet Agarwal, Purushottam Kar, and Manik Varma. 2021. Decaf: Deep extreme classification with label features. In WSDM\u201921. 49\u201357."},{"key":"e_1_3_2_2_30_1","volume-title":"ECLARE: Extreme Classification with Label Graph Correlations. In WWW\u201921. 3721\u20133732.","author":"Mittal Anshul","year":"2021","unstructured":"Anshul Mittal, Noveen Sachdeva, Sheshansh Agrawal, Sumeet Agarwal, Purushottam Kar, and Manik Varma. 2021. ECLARE: Extreme Classification with Label Graph Correlations. In WWW\u201921. 3721\u20133732."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btw294"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"crossref","unstructured":"Yashoteja Prabhu Anil Kag Shilpa Gopinath Kunal Dahiya Shrutendra Harsola Rahul Agrawal and Manik Varma. 2018. Extreme multi-label learning with label features for warm-start tagging ranking & recommendation. In WSDM\u201918. 441\u2013449.","DOI":"10.1145\/3159652.3159660"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3185998"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623651"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0018209"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"crossref","unstructured":"Deepak Saini Arnav\u00a0Kumar Jain Kushal Dave Jian Jiao Amit Singh Ruofei Zhang and Manik Varma. 2021. GalaXC: Graph Neural Networks with Labelwise Attention for Extreme Classification. In WWW\u201921. 3733\u20133744.","DOI":"10.1145\/3442381.3449937"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"crossref","unstructured":"Zhihong Shen Hao Ma and Kuansan Wang. 2018. A Web-scale system for scientific knowledge exploration. In ACL\u201918 System Demonstrations. 87\u201392.","DOI":"10.18653\/v1\/P18-4015"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"crossref","unstructured":"Arnab Sinha Zhihong Shen Yang Song Hao Ma Darrin Eide Bo-June Hsu and Kuansan Wang. 2015. An overview of microsoft academic service (mas) and applications. In WWW\u201915 Companion. 243\u2013246.","DOI":"10.1145\/2740908.2742839"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3097987"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"crossref","unstructured":"Jie Tang Jing Zhang Limin Yao Juanzi Li Li Zhang and Zhong Su. 2008. Arnetminer: extraction and mining of academic social networks. In KDD\u201908. 990\u2013998.","DOI":"10.1145\/1401890.1402008"},{"key":"e_1_3_2_2_41_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In NIPS\u201917. 5998\u20136008."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1162\/qss_a_00021"},{"key":"e_1_3_2_2_43_1","volume-title":"Is preprint the future of science? A thirty year journey of online preprint services. arXiv preprint arXiv:2102.09066","author":"Xie Boya","year":"2021","unstructured":"Boya Xie, Zhihong Shen, and Kuansan Wang. 2021. Is preprint the future of science? A thirty year journey of online preprint services. arXiv preprint arXiv:2102.09066 (2021)."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"crossref","unstructured":"Guangxu Xun Kishlay Jha Jianhui Sun and Aidong Zhang. 2020. Correlation networks for extreme multi-label text classification. In KDD\u201920. 1074\u20131082.","DOI":"10.1145\/3394486.3403151"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz142"},{"key":"e_1_3_2_2_46_1","volume-title":"Xlnet: Generalized autoregressive pretraining for language understanding. NeurIPS\u201919.","author":"Yang Zhilin","year":"2019","unstructured":"Zhilin Yang, Zihang Dai, Yiming Yang, Jaime Carbonell, Russ\u00a0R Salakhutdinov, and Quoc\u00a0V Le. 2019. Xlnet: Generalized autoregressive pretraining for language understanding. NeurIPS\u201919."},{"key":"e_1_3_2_2_47_1","volume-title":"Beyond Text: Incorporating Metadata and Label Structure for Multi-Label Document Classification using Heterogeneous Graphs. In EMNLP\u201921. 3162\u20133171.","author":"Ye Chenchen","year":"2021","unstructured":"Chenchen Ye, Linhai Zhang, Yulan He, Deyu Zhou, and Jie Wu. 2021. Beyond Text: Incorporating Metadata and Label Structure for Multi-Label Document Classification using Heterogeneous Graphs. In EMNLP\u201921. 3162\u20133171."},{"key":"e_1_3_2_2_48_1","unstructured":"Hui Ye Zhiyu Chen Da-Han Wang and Brian Davison. 2020. Pretrained generalized autoregressive model with adaptive probabilistic label clusters for extreme multi-label text classification. In ICML\u201920. 10809\u201310819."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098083"},{"key":"e_1_3_2_2_50_1","volume-title":"Pd-sparse: A primal and dual sparse approach to extreme multiclass and multilabel classification. In ICML\u201916. 3069\u20133077.","author":"En-Hsu Yen Ian","year":"2016","unstructured":"Ian En-Hsu Yen, Xiangru Huang, Pradeep Ravikumar, Kai Zhong, and Inderjit Dhillon. 2016. Pd-sparse: A primal and dual sparse approach to extreme multiclass and multilabel classification. In ICML\u201916. 3069\u20133077."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-022-01397-5"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btaa837"},{"key":"e_1_3_2_2_53_1","volume-title":"Attentionxml: Label tree-based attention-aware deep model for high-performance extreme multi-label text classification. NeurIPS\u201919","author":"You Ronghui","year":"2019","unstructured":"Ronghui You, Zihan Zhang, Ziye Wang, Suyang Dai, Hiroshi Mamitsuka, and Shanfeng Zhu. 2019. Attentionxml: Label tree-based attention-aware deep model for high-performance extreme multi-label text classification. NeurIPS\u201919 (2019), 5820\u20135830."},{"key":"e_1_3_2_2_54_1","first-page":"1","article-title":"PECOS: Prediction for enormous and correlated output spaces","volume":"23","author":"Yu Hsiang-Fu","year":"2022","unstructured":"Hsiang-Fu Yu, Kai Zhong, Jiong Zhang, Wei-Cheng Chang, and Inderjit\u00a0S Dhillon. 2022. PECOS: Prediction for enormous and correlated output spaces. JMLR 23, 98 (2022), 1\u201332.","journal-title":"JMLR"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330785"},{"key":"e_1_3_2_2_56_1","unstructured":"Jiong Zhang Wei-Cheng Chang Hsiang-Fu Yu and Inderjit Dhillon. 2021. Fast multi-resolution transformer fine-tuning for extreme multi-label text classification. In NeurIPS\u201921. 7267\u20137280."},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"crossref","unstructured":"Yu Zhang Xiusi Chen Yu Meng and Jiawei Han. 2021. Hierarchical Metadata-Aware Document Categorization under Weak Supervision. In WSDM\u201921. 770\u2013778.","DOI":"10.1145\/3437963.3441730"},{"key":"e_1_3_2_2_58_1","volume-title":"Motifclass: Weakly supervised text classification with higher-order metadata information. In WSDM\u201922. 1357\u20131367.","author":"Zhang Yu","year":"2022","unstructured":"Yu Zhang, Shweta Garg, Yu Meng, Xiusi Chen, and Jiawei Han. 2022. Motifclass: Weakly supervised text classification with higher-order metadata information. In WSDM\u201922. 1357\u20131367."},{"key":"e_1_3_2_2_59_1","volume-title":"MATCH: Metadata-Aware Text Classification in A Large Hierarchy. In WWW\u201921. 3246\u20133257.","author":"Zhang Yu","year":"2021","unstructured":"Yu Zhang, Zhihong Shen, Yuxiao Dong, Kuansan Wang, and Jiawei Han. 2021. MATCH: Metadata-Aware Text Classification in A Large Hierarchy. In WWW\u201921. 3246\u20133257."},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"crossref","unstructured":"Yu Zhang Zhihong Shen Chieh-Han Wu Boya Xie Junheng Hao Ye-Yi Wang Kuansan Wang and Jiawei Han. 2022. Metadata-Induced Contrastive Learning for Zero-Shot Multi-Label Text Classification. In WWW\u201922. 3162\u20133173.","DOI":"10.1145\/3485447.3512174"}],"event":{"name":"WWW '23: The ACM Web Conference 2023","location":"Austin TX USA","acronym":"WWW '23","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2023"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543507.3583354","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3543507.3583354","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3543507.3583354","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3543507.3583354","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:23Z","timestamp":1750178243000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543507.3583354"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,30]]},"references-count":60,"alternative-id":["10.1145\/3543507.3583354","10.1145\/3543507"],"URL":"https:\/\/doi.org\/10.1145\/3543507.3583354","relation":{},"subject":[],"published":{"date-parts":[[2023,4,30]]},"assertion":[{"value":"2023-04-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}