These models can be used out-of-the-box for sentence encoding tasks such as semantic search, clustering, and topic modelling.
CrisisTransformers
university
AI & ML interests
Crisis informatics
Organization Card
CrisisTransformers | State-of-the-art contextual and semantically meaningful sentence embeddings for crisis-related social media texts
CrisisTransformers is a family of pre-trained language models and sentence encoders introduced in the papers "CrisisTransformers: Pre-trained language models and sentence encoders for crisis-related social media texts" and "Semantically Enriched Cross-Lingual Sentence Embeddings for Crisis-related Social Media Texts".
The models were trained on a massive corpus of over 15 billion word tokens from tweets associated with 30+ crisis events, such as disease outbreaks, natural disasters, conflicts, etc.
models
11
crisistransformers/CT-M1-BestLoss
Fill-Mask
•
Updated
•
22
crisistransformers/CT-M3-Complete
Fill-Mask
•
Updated
•
102
•
1
crisistransformers/CT-M3-BestLoss
Fill-Mask
•
Updated
•
10
crisistransformers/CT-M3-OneLook
Fill-Mask
•
Updated
•
14
crisistransformers/CT-M2-Complete
Fill-Mask
•
Updated
•
26
crisistransformers/CT-M2-BestLoss
Fill-Mask
•
Updated
•
11
crisistransformers/CT-M2-OneLook
Fill-Mask
•
Updated
•
17
crisistransformers/CT-M1-Complete
Fill-Mask
•
Updated
•
150
crisistransformers/CT-M1-Complete-SE
Sentence Similarity
•
Updated
•
6
•
1
crisistransformers/CT-mBERT-SE
Sentence Similarity
•
Updated
•
9
datasets
None public yet