1.1
1
xml
info:srw/schema/1/mods-v3.2
Transformer-based Multi-task Learning for Disaster Tweet Categorisation
Congcong Wang
author
Paul Nulty
author
David Lillis
author
2021
Virginia Tech
Blacksburg, VA (USA)
English
Social media has enabled people to circulate information in a timely fashion, thus motivating people to post messages seeking help during crisis situations. These messages can contribute to the situational awareness of emergency responders, who have a need for them to be categorised according to information types (i.e. the type of aid services the messages are requesting). We introduce a transformer-based multi-task learning (MTL) technique for classifying information types and estimating the priority of these messages. We evaluate the effectiveness of our approach with a variety of metrics by submitting runs to the TREC Incident Streams (IS) track: a research initiative specifically designed for disaster tweet classification and prioritisation. The results demonstrate that our approach achieves competitive performance in most metrics as compared to other participating runs. Subsequently, we find that an ensemble approach combining disparate transformer encoders within our approach helps to improve the overall effectiveness to a significant extent, achieving state-of-the-art performance in almost every metric. We make the code publicly available so that our work can be reproduced and used as a baseline for the community for future work in this domain.
Disaster Response
Tweet Analysis
Transformers
Natural Language Processing
wangcongcongcc@gmail.com
exported from refbase (http://idl.iscram.org/show.php?record=2366), last updated on Tue, 13 Jul 2021 18:38:21 +0200
text
http://idl.iscram.org/files/congcongwang/2021/2366_CongcongWang_etal2021.pdf
CongcongWang_etal2021
ISCRAM 2021 Conference Proceedings – 18th International Conference on Information Systems for Crisis Response and Management
Iscram 2021
Anouck Adrot
editor
Rob Grace
editor
Kathleen Moore
editor
Christopher W. Zobel
editor
18th International Conference on Information Systems for Crisis Response and Management
2021
Virginia Tech
Blacksburg, VA (USA)
conference publication
705
718
978-1-949373-61-5
1