Emory at WNUT-2020 Task 2: Combining Pretrained Deep Learning Models and Feature Enrichment for Informative Tweet Identification

Yuting Guo, Mohammed Ali Al-Garadi, Abeed Sarker


Abstract
This paper describes the system developed by the Emory team for the WNUT-2020 Task 2: “Identifi- cation of Informative COVID-19 English Tweet”. Our system explores three recent Transformer- based deep learning models pretrained on large- scale data to encode documents. Moreover, we developed two feature enrichment methods to en- hance document embeddings by integrating emoji embeddings and syntactic features into deep learn- ing models. Our system achieved F1-score of 0.897 and accuracy of 90.1% on the test set, and ranked in the top-third of all 55 teams.
Anthology ID:
2020.wnut-1.54
Volume:
Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)
Month:
November
Year:
2020
Address:
Online
Venues:
EMNLP | WNUT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
388–393
Language:
URL:
https://www.aclweb.org/anthology/2020.wnut-1.54
DOI:
10.18653/v1/2020.wnut-1.54
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.wnut-1.54.pdf