Presents a low-supervision urgency detection system using ensembles and transfer learning that outperforms baselines on multiple disaster datasets.
Learning from the crowd: col- laborative filtering techniques for identifying on-the-ground twitterers during mass disruptions,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Low-supervision urgency detection and transfer in short crisis messages
Presents a low-supervision urgency detection system using ensembles and transfer learning that outperforms baselines on multiple disaster datasets.