Document Classification for COVID-19 Literature
| Autor: | Juncheng Zeng, Dongdong Zhang, Ping Zhang, Bernal Jiménez Gutiérrez, Yu Su |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
0303 health sciences Information retrieval Computer Science - Computation and Language business.industry Computer science Document classification 02 engineering and technology Scientific literature computer.software_genre Computer Science - Information Retrieval 03 medical and health sciences Text mining Discriminative model Margin (machine learning) 020204 information systems Test set 0202 electrical engineering electronic engineering information engineering Language model Computational linguistics business Computation and Language (cs.CL) computer Information Retrieval (cs.IR) 030304 developmental biology |
| Zdroj: | EMNLP (Findings) |
| Popis: | The global pandemic has made it more important than ever to quickly and accurately retrieve relevant scientific literature for effective consumption by researchers in a wide range of fields. We provide an analysis of several multi-label document classification models on the LitCovid dataset, a growing collection of 23,000 research papers regarding the novel 2019 coronavirus. We find that pre-trained language models fine-tuned on this dataset outperform all other baselines and that BioBERT surpasses the others by a small margin with micro-F1 and accuracy scores of around 86% and 75% respectively on the test set. We evaluate the data efficiency and generalizability of these models as essential features of any system prepared to deal with an urgent situation like the current health crisis. Finally, we explore 50 errors made by the best performing models on LitCovid documents and find that they often (1) correlate certain labels too closely together and (2) fail to focus on discriminative sections of the articles; both of which are important issues to address in future work. Both data and code are available on GitHub. 8 pages, 9 figures |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|