VinAI at ChEMU 2020: An accurate system for named entity recognition in chemical reactions from patents

Abstract

This paper describes our VinAI system for the ChEMU task 1 of named entity recognition (NER) in chemical reactions. Our system employs a BiLSTM-CNN-CRF architecture with additional contextualized word embeddings. It achieves very high performance, officially ranking second with regards to both exact- and relaxed-match F1 scores at 94.33% and 96.84%, respectively. In a post-evaluation phase, fixing a mapping bug which converts the column-based format into the brat standoff format helps our system to obtain higher results. In particular, we obtain an exact-match F1 score at 95.21% and especially a relaxed-match F1 score at 97.26%, thus achieving the highest relaxed-match F1 compared to all other participating systems. We believe our system can serve as a strong baseline for future research and downstream applications of chemical NER over chemical reactions from patents.