@inproceedings{6cbdd86dd0b84707aae1d52649c72a9b,
title = "REACTCLASS: Cross-Modal Supervision for Subword-Guided Reactant Entity Classification",
abstract = "We propose REACTCLASS that automatically maps the low-level concrete chemical entities into the high-level reactant groups without human effort for training data annotation. REACTCLASS is designed to take two special characteristics of the chemical molecules into consideration. The first characteristic is that each chemical molecule can be represented in two modalities: a chemical name in the text and a molecular structure in the graph. We propose to use cross-modal supervision to automatically create the training data for chemical name classification in the text via molecular structure matching in the graph. The second characteristic is that there is a knowledge-aware subword correlation between the surface names of the chemical entities to be classified and that of the reactant groups as class labels. We propose to train a classification model based on the subword cross-attention map between each chemical name and the corresponding reaction group. Experiments demonstrate that REACTCLASS is highly effective, achieving state-of-the-art performance in classifying the chemical names into human-defined reactant groups without requiring human effort for training data annotation.",
keywords = "Attention Map Representation, Chemistry Text Mining, Cross-Modal Supervised Learning",
author = "Xuan Wang and Vivian Hu and Minhao Jiang and Yu Zhang and Jinfeng Xiao and Loving, \{Danielle Cherrice\} and Heng Ji and Martin Burke and Jiawei Han",
note = "ACKNOWLEDGMENTS Research was supported in part by US DARPA KAIROS Program No. FA8750-19-2-1004 and INCAS Program No. HR001121C0165, National Science Foundation IIS-19-56151, IIS-17-41317, and IIS 17-04532, and the Molecule Maker Lab Institute: An AI Research Institutes program supported by NSF under Award No. 2019897, and the Institute for Geospatial Understanding through an Integrative Discovery Environment (I-GUIDE) by NSF under Award No. 2118329. Any opinions, findings, and conclusions or recommendations expressed herein are those of the authors and do not necessarily represent the views, either expressed or implied, of DARPA or the U.S. Government.; 2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022 ; Conference date: 06-12-2022 Through 08-12-2022",
year = "2022",
doi = "10.1109/BIBM55620.2022.9995489",
language = "English (US)",
series = "Proceedings - 2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "844--847",
editor = "Donald Adjeroh and Qi Long and Xinghua Shi and Fei Guo and Xiaohua Hu and Srinivas Aluru and Giri Narasimhan and Jianxin Wang and Mingon Kang and Mondal, \{Ananda M.\} and Jin Liu",
booktitle = "Proceedings - 2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022",
address = "United States",
}