AUTHOR=Mahendran Darshini , Gurdin Gabrielle , Lewinski Nastassja , Tang Christina , McInnes Bridget T. TITLE=Identifying Chemical Reactions and Their Associated Attributes in Patents JOURNAL=Frontiers in Research Metrics and Analytics VOLUME=Volume 6 - 2021 YEAR=2021 URL=https://www.frontiersin.org/journals/research-metrics-and-analytics/articles/10.3389/frma.2021.688353 DOI=10.3389/frma.2021.688353 ISSN=2504-0537 ABSTRACT=Chemical patents are an important source of information about novel chemicals and chemical reactions. With the increasing volume of such patents, mining information about these chemicals and chemical reactions has become a time-intensive and laborious endeavor. In this paper, we present a system to automatically extract chemical reaction events from patents. Our approach consists of two steps: 1) Named Entity Recognition (NER) -- the automatic identification of chemical reaction parameters from the corresponding text; and 2) Event Extraction (EE) -- the automatic classifying and linking of entities based on their relationships to each other. For our NER system, we evaluate Bidirectional Long Short Term Memory (BiLSTM)-based and Bidirectional Encoder Representations from Transformers (BERT)-based methods. For our RE system, we evaluate two BERT-based, Convolutional Neural Networks (CNN)-based, and rule-based methods. We evaluate our NER and EE components separately and also as an end-to-end system, reporting the precision, recall, and F- score. From the results, we can conclude the BiLSTM-based method performed well at identifying the entities, and the CNN-based method performed well at extracting events. CNN-based and BERT-based methods performed well with the classes with more instances to train on, and the rule-based method performed well with classes with fewer instances.