WNUT-2020 Task 1 Overview: Extracting Entities and Relations from Wet Lab Protocols

TL;DR

This paper summarizes the WNUT 2020 shared task on extracting entities and relations from wet lab protocols, detailing the task setup, data annotation, and system performances.

Contribution

It provides a comprehensive overview of the wet lab information extraction challenge, including dataset creation and system approaches for NER and RE tasks.

Findings

Multiple systems achieved competitive NER performance.

Relation extraction systems demonstrated promising results.

The dataset and task setup facilitate future research in wet lab information extraction.

Abstract

This paper presents the results of the wet lab information extraction task at WNUT 2020. This task consisted of two sub tasks: (1) a Named Entity Recognition (NER) task with 13 participants and (2) a Relation Extraction (RE) task with 2 participants. We outline the task, data annotation process, corpus statistics, and provide a high-level overview of the participating systems for each sub task.