TEST_POSITIVE at W-NUT 2020 Shared Task-3: Joint Event Multi-task Learning for Slot Filling in Noisy Text

TL;DR

This paper presents JOELIN, a joint multi-task learning model for extracting COVID-19 related events from noisy Twitter data, improving slot filling accuracy through unified training and post-processing.

Contribution

The paper introduces JOELIN, a novel multi-task learning framework that leverages all available data and type-aware post-processing to enhance event extraction from noisy social media text.

Findings

JOELIN outperforms BERT baseline by 17.2% in micro F1.

Unified multi-task learning improves slot filling accuracy.

Type-aware post-processing filters predictions effectively.

Abstract

The competition of extracting COVID-19 events from Twitter is to develop systems that can automatically extract related events from tweets. The built system should identify different pre-defined slots for each event, in order to answer important questions (e.g., Who is tested positive? What is the age of the person? Where is he/she?). To tackle these challenges, we propose the Joint Event Multi-task Learning (JOELIN) model. Through a unified global learning framework, we make use of all the training data across different events to learn and fine-tune the language model. Moreover, we implement a type-aware post-processing procedure using named entity recognition (NER) to further filter the predictions. JOELIN outperforms the BERT baseline by 17.2% in micro F1.