Improving Tagging Consistency and Entity Coverage for Chemical Identification in Full-text Articles

TL;DR

This paper presents a system that enhances chemical entity recognition in full-text articles by improving tagging consistency and coverage, achieving top performance in the BioCreative VII challenge.

Contribution

It introduces a hybrid approach combining dictionary and neural models, along with majority voting, to improve chemical NER in full-text articles, outperforming existing methods.

Findings

Achieved highest NER performance in BioCreative VII challenge

Significantly improved recall over baseline models

Outperformed over 80 submissions from 16 teams

Abstract

This paper is a technical report on our system submitted to the chemical identification task of the BioCreative VII Track 2 challenge. The main feature of this challenge is that the data consists of full-text articles, while current datasets usually consist of only titles and abstracts. To effectively address the problem, we aim to improve tagging consistency and entity coverage using various methods such as majority voting within the same articles for named entity recognition (NER) and a hybrid approach that combines a dictionary and a neural model for normalization. In the experiments on the NLM-Chem dataset, we show that our methods improve models' performance, particularly in terms of recall. Finally, in the official evaluation of the challenge, our system was ranked 1st in NER by significantly outperforming the baseline model and more than 80 submissions from 16 teams.