Big Green at WNUT 2020 Shared Task-1: Relation Extraction as Contextualized Sequence Classification

TL;DR

This paper presents a system that uses contextualized knowledge graph completion for relation and event extraction in noisy text, demonstrating effectiveness on wet lab protocol data.

Contribution

It introduces a novel approach combining contextualized knowledge graph completion with relation and event extraction in noisy environments.

Findings

Effective relation and event extraction from wet lab protocols

System outperforms baseline methods in noisy text environments

Demonstrates applicability in scientific protocol analysis

Abstract

Relation and event extraction is an important task in natural language processing. We introduce a system which uses contextualized knowledge graph completion to classify relations and events between known entities in a noisy text environment. We report results which show that our system is able to effectively extract relations and events from a dataset of wet lab protocols.