UCD-CS at W-NUT 2020 Shared Task-3: A Text to Text Approach for COVID-19 Event Extraction on Social Media

Files in This Item:
File Description SizeFormat 
Wang2020c.pdf365.79 kBAdobe PDFDownload
Title: UCD-CS at W-NUT 2020 Shared Task-3: A Text to Text Approach for COVID-19 Event Extraction on Social Media
Authors: Wang, CongcongLillis, David
Permanent link: http://hdl.handle.net/10197/12049
Date: 19-Nov-2020
Online since: 2021-03-18T12:57:52Z
Abstract: In this paper, we describe our approach in the shared task: COVID-19 event extraction from Twitter. The objective of this task is to extract answers from COVID-related tweets to a set of predefined slot-filling questions. Our approach treats the event extraction task as a question answering task by leveraging the transformer-based T5 text-to-text model. According to the official evaluation scores returned, namely F1, our submitted run achieves competitive performance compared to other participating runs (Top 3). However, we argue that this evaluation may underestimate the actual performance of runs based on text-generation. Although some such runs may answer the slot questions well, they may not be an exact string match for the gold standard answers. To measure the extent of this underestimation, we adopt a simple exact-answer transformation method aiming at converting the well-answered predictions to exactly-matched predictions. The results show that after this transformation our run overall reaches the same level of performance as the best participating run and state-of-the-art F1 scores in three of five COVID-related events. Our code is publicly available to aid reproducibility
Type of material: Conference Publication
Publisher: Association for Computational Linguistics
Keywords: COVID-19CoronavirusNews eventsEvent extractionComputational linguistic techniquesTwitter
DOI: 10.18653/v1/2020.wnut-1.78
Other versions: http://noisy-text.github.io/2020/
Language: en
Status of Item: Peer reviewed
Is part of: Xu, W., Ritter, A., Baldwin, T., Rahimi, A. (eds.). Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)
Conference Details: The 6th Workshop on Noisy User-generated Text (W-NUT 2020), Virtual Workshop,19 November 2020
This item is made available under a Creative Commons License: https://creativecommons.org/licenses/by/3.0/ie/
Appears in Collections:Computer Science Research Collection

Show full item record

Page view(s)

56
Last Week
8
Last month
checked on Apr 11, 2021

Download(s)

8
checked on Apr 11, 2021

Google ScholarTM

Check

Altmetric


If you are a publisher or author and have copyright concerns for any item, please email research.repository@ucd.ie and the item will be withdrawn immediately. The author or person responsible for depositing the article will be contacted within one business day.