{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T10:27:54Z","timestamp":1751884074208,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,8,14]],"date-time":"2022-08-14T00:00:00Z","timestamp":1660435200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["FA8750-19-2-1004"],"award-info":[{"award-number":["FA8750-19-2-1004"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2019897"],"award-info":[{"award-number":["2019897"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,8,14]]},"DOI":"10.1145\/3534678.3542606","type":"proceedings-article","created":{"date-parts":[[2022,8,12]],"date-time":"2022-08-12T19:06:12Z","timestamp":1660331172000},"page":"4832-4833","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["New Frontiers of Scientific Text Mining"],"prefix":"10.1145","author":[{"given":"Xuan","family":"Wang","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Champaign, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongwei","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Champaign, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heng","family":"Ji","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Champaign, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiawei","family":"Han","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Champaign, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,8,14]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Donald C Comeau, W John Wilbur, and Zhiyong Lu.","author":"Allot Alexis","year":"2019","unstructured":"Alexis Allot, Qingyu Chen, Sun Kim, Roberto Vera Alvarez, Donald C Comeau, W John Wilbur, and Zhiyong Lu. 2019. LitSense: making sense of biomedical literature at sentence level. Nucleic acids research (2019)."},{"key":"e_1_3_2_1_2_1","volume-title":"ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction. ArXiv preprint","author":"Chithrananda Seyone","year":"2020","unstructured":"Seyone Chithrananda, Gabe Grand, and Bharath Ramsundar. 2020. ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction. ArXiv preprint, Vol. abs\/2010.09885 (2020)."},{"key":"e_1_3_2_1_3_1","volume-title":"Molecular representation learning with language models and domain-relevant auxiliary tasks. arXiv preprint arXiv:2011.13230","author":"Fabian Benedek","year":"2020","unstructured":"Benedek Fabian, Thomas Edlich, H\u00e9l\u00e9na Gaspar, Marwin Segler, Joshua Meyers, Marco Fiscato, and Mohamed Ahmed. 2020. Molecular representation learning with language models and domain-relevant auxiliary tasks. arXiv preprint arXiv:2011.13230 (2020)."},{"key":"e_1_3_2_1_4_1","volume-title":"Saber A Akhondi, Christian Druckenbrodt, Camilo Thorne, Ralph Hoessel, Zubair Afzal, Zenan Zhai, Biaoyan Fang, Hiyori Yoshikawa, et almbox.","author":"He Jiayuan","year":"2020","unstructured":"Jiayuan He, Dat Quoc Nguyen, Saber A Akhondi, Christian Druckenbrodt, Camilo Thorne, Ralph Hoessel, Zubair Afzal, Zenan Zhai, Biaoyan Fang, Hiyori Yoshikawa, et almbox. 2020. Overview of ChEMU 2020: named entity recognition and event extraction of chemical reactions from patents. In CLEF. Springer, 237--254."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.7b00616"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1186\/1758-2946-7-S1-S1"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Tuan Lai Heng Ji ChengXiang Zhai and Quan Hung Tran. 2021. Joint Biomedical Entity and Relation Extraction with Knowledge-Enhanced Collective Inference. In ACL. 6248--6260.","DOI":"10.18653\/v1\/2021.acl-long.488"},{"key":"e_1_3_2_1_8_1","volume-title":"Gaia: A fine-grained multimedia knowledge extraction system. In ACL. 77--86.","author":"Li Manling","year":"2020","unstructured":"Manling Li, Alireza Zareian, Ying Lin, Xiaoman Pan, Spencer Whitehead, Brian Chen, Bo Wu, Heng Ji, Shih-Fu Chang, Clare Voss, et al. 2020. Gaia: A fine-grained multimedia knowledge extraction system. In ACL. 77--86."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Qi Li Xuan Wang Yu Zhang Fei Ling Cathy Wu H and Jiawei Han. 2018. Pattern Discovery for Wide-Window Open Information Extraction in Biomedical Literature. In BIBM. 420--427.","DOI":"10.1109\/BIBM.2018.8621375"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1152\/ajpheart.00175.2018"},{"key":"e_1_3_2_1_11_1","unstructured":"Emily K Mallory Ambika Acharya Stefano E Rensi Peter J Turnbaugh Roselie A Bright and Russ B Altman. 2018. Chemical reaction vector embeddings: towards predicting drug metabolism in the human gut microbiome. In PSB. 56--67."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pbio.0020309"},{"key":"e_1_3_2_1_13_1","volume-title":"YAGO: A multilingual knowledge base from wikipedia, wordnet, and geonames","author":"Rebele Thomas","year":"2016","unstructured":"Thomas Rebele, Fabian Suchanek, Johannes Hoffart, Joanna Biega, Erdal Kuzey, and Gerhard Weikum. 2016. YAGO: A multilingual knowledge base from wikipedia, wordnet, and geonames. In ISWC. Springer, 177--185."},{"key":"e_1_3_2_1_14_1","volume-title":"Life-inet: A structured network-based knowledge exploration and analytics system for life sciences. In ACL. 55--60.","author":"Ren Xiang","year":"2017","unstructured":"Xiang Ren, Jiaming Shen, Meng Qu, Xuan Wang, Zeqiu Wu, Qi Zhu, Meng Jiang, Fangbo Tao, Saurabh Sinha, David Liem, et al. 2017. Life-inet: A structured network-based knowledge exploration and analytics system for life sciences. In ACL. 55--60."},{"key":"e_1_3_2_1_15_1","volume-title":"Flexible analog search with kernel PCA embedded molecule vectors. Computational and structural biotechnology journal","author":"Rensi Stefano","year":"2017","unstructured":"Stefano Rensi and Russ B Altman. 2017. Flexible analog search with kernel PCA embedded molecule vectors. Computational and structural biotechnology journal, Vol. 15 (2017), 320--327."},{"key":"e_1_3_2_1_16_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. 243--246.","DOI":"10.1145\/2740908.2742839"},{"key":"e_1_3_2_1_17_1","volume-title":"Rapidly Bootstrapping a Question Answering Dataset for COVID-19. arXiv preprint arXiv:2004.11339","author":"Tang Raphael","year":"2020","unstructured":"Raphael Tang, Rodrigo Nogueira, Edwin Zhang, Nikhil Gupta, Phuong Cam, Kyunghyun Cho, and Jimmy Lin. 2020. Rapidly Bootstrapping a Question Answering Dataset for COVID-19. arXiv preprint arXiv:2004.11339 (2020)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"George Tsatsaronis Georgios Balikas Prodromos Malakasiotis Ioannis Partalas Matthias Zschunke Michael R Alvers Dirk Weissenborn Anastasia Krithara Sergios Petridis Dimitris Polychronopoulos et al. 2015. An overview of the BIOASQ large-scale biomedical semantic indexing and question answering competition. BMC bioinformatics Vol. 16 1 (2015) 138.","DOI":"10.1186\/s12859-015-0564-6"},{"key":"e_1_3_2_1_19_1","volume-title":"Database","volume":"2018","author":"Valenzuela-Esc\u00e1rcega Marco A","year":"2018","unstructured":"Marco A Valenzuela-Esc\u00e1rcega, \u00d6zg\u00fcn Babur, Gus Hahn-Powell, Dane Bell, Thomas Hicks, Enrique Noriega-Atala, Xia Wang, Mihai Surdeanu, Emek Demir, and Clayton T Morrison. 2018. Large-scale automated machine reading discovers new cancer-driving mechanisms. Database, Vol. 2018 (2018)."},{"key":"e_1_3_2_1_20_1","volume-title":"2021 b. Chemical-Reaction-Aware Molecule Representation Learning. ICLR","author":"Wang Hongwei","year":"2021","unstructured":"Hongwei Wang, Weijiang Li, Xiaomeng Jin, Kyunghyun Cho, Heng Ji, Jiawei Han, and Martin D Burke. 2021 b. Chemical-Reaction-Aware Molecule Representation Learning. ICLR (2021)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Qingyun Wang Manling Li Xuan Wang Nikolaus Parulian Guangxing Han Jiawei Ma Jingxuan Tu Ying Lin Ranran Haoran Zhang Weili Liu et al. 2021 c. COVID-19 Literature Knowledge Graph Construction and Drug Repurposing Report Generation. In NAACL. 66--77.","DOI":"10.18653\/v1\/2021.naacl-demos.8"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Xuan Wang Yingjun Guan Weili Liu Aabhas Chauhan Enyi Jiang Qi Li David Liem Dibakar Sigdel John Caufield Peipei Ping and Jiawei Han. 2020 a. EVIDENCEMINER: Textual Evidence Discovery for Life Sciences. In ACL. 56--62.","DOI":"10.18653\/v1\/2020.acl-demos.8"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Xuan Wang Vivian Hu Xiangchen Song Shweta Garg Jinfeng Xiao and Jiawei Han. 2021 a. ChemNER: Fine-Grained Chemistry Named Entity Recognition with Ontology-guided Distant Supervision. In EMNLP. 5227--5240.","DOI":"10.18653\/v1\/2021.emnlp-main.424"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Xuan Wang Xiangchen Song Bangzheng Li Kang Zhou Qi Li and Jiawei Han. 2020 b. Fine-Grained Named Entity Recognition with Distant Supervision in COVID-19 Literature. In BIBM. 491--494.","DOI":"10.1109\/BIBM49941.2020.9313126"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Xuan Wang Yu Zhang Aabhas Chauhan Qi Li and Jiawei Han. 2020 c. Textual Evidence Mining via Spherical Heterogeneous Information Network Embedding. In BigData. 828--837.","DOI":"10.1109\/BigData50022.2020.9377958"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Xuan Wang Yu Zhang Qi Li Yinyin Chen and Jiawei Han. 2018. Open Information Extraction with Meta-pattern Discovery in Biomedical Literature. In BCB. 291--300.","DOI":"10.1145\/3233547.3233594"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Xuan Wang Yu Zhang Qi Li Xiang Ren Jingbo Shang and Jiawei Han. 2019. Distantly supervised biomedical named entity recognition with dictionary expansion. In BIBM. 496--503.","DOI":"10.1109\/BIBM47256.2019.8983212"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Taiki Watanabe Akihiro Tamura Takashi Ninomiya Takuya Makino and Tomoya Iwakura. 2019. Multi-Task Learning for Chemical Named Entity Recognition with Chemical Compound Paraphrasing. In EMNLP-IJCNLP. 6244--6249.","DOI":"10.18653\/v1\/D19-1648"},{"key":"e_1_3_2_1_29_1","volume-title":"PubTator: a web-based text mining tool for assisting biocuration. Nucleic acids research","author":"Wei Chih-Hsuan","year":"2013","unstructured":"Chih-Hsuan Wei, Hung-Yu Kao, and Zhiyong Lu. 2013. PubTator: a web-based text mining tool for assisting biocuration. Nucleic acids research, Vol. 41, W1 (2013), W518--W522."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Zixuan Zhang Nikolaus Parulian Heng Ji Ahmed Elsayed Skatje Myers and Martha Palmer. 2021. Fine-grained Information Extraction from Biomedical Literature based on Knowledge-enriched Abstract Meaning Representation. In ACL. 6261--6270.","DOI":"10.18653\/v1\/2021.acl-long.489"}],"event":{"name":"KDD '22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"],"location":"Washington DC USA","acronym":"KDD '22"},"container-title":["Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3542606","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3534678.3542606","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3534678.3542606","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:03:04Z","timestamp":1750186984000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3542606"}},"subtitle":["Tasks, Data, and Tools"],"short-title":[],"issued":{"date-parts":[[2022,8,14]]},"references-count":30,"alternative-id":["10.1145\/3534678.3542606","10.1145\/3534678"],"URL":"https:\/\/doi.org\/10.1145\/3534678.3542606","relation":{},"subject":[],"published":{"date-parts":[[2022,8,14]]},"assertion":[{"value":"2022-08-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}