issues
search
alecokas
/
swahili-text-gcn
Graph Convolutional Network for Swahili News Classification: https://arxiv.org/abs/2103.09325
https://arxiv.org/abs/2103.09325
MIT License
8
stars
4
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
tf-idz.npz not found
#43
TheGiantDad
closed
3 years ago
14
Add argument for text2vec types
#42
alecokas
closed
3 years ago
0
Clean up
#41
alecokas
closed
3 years ago
0
added plotting functions
#40
tyler-martin-12
closed
3 years ago
1
Add macro f1 to GCN
#39
alecokas
closed
3 years ago
0
Add f1 metric to baseline models
#38
alecokas
closed
3 years ago
0
Updated baselines for test set
#37
alecokas
closed
3 years ago
0
Save test predictions
#36
alecokas
closed
3 years ago
0
Manual split
#35
alecokas
closed
3 years ago
0
Make adjacency matrix symmetric (and add t-SNE)
#34
alecokas
closed
3 years ago
0
Bug fix and also name baseline model dirs with label prop
#33
alecokas
closed
3 years ago
0
Added line for training loss to training plot
#32
tyler-martin-12
closed
3 years ago
0
Window CLI and subdirectory renaming
#31
alecokas
closed
3 years ago
0
Bash scripts to sequentially run experiments
#30
alecokas
closed
3 years ago
0
WIP: Document indices and simpler train/val split
#29
tyler-martin-12
closed
3 years ago
0
Count model and mini-refactor
#28
alecokas
closed
3 years ago
0
Stemming bug fix
#27
tyler-martin-12
closed
3 years ago
0
Text2Vec as node feature inputs
#26
alecokas
closed
3 years ago
2
Auto-deletion for old checkpoints
#25
tyler-martin-12
closed
3 years ago
1
added create_training_plot function and notebook
#24
tyler-martin-12
closed
3 years ago
1
Doc2vec + LR and others
#23
alecokas
closed
3 years ago
1
Add Averaged FastText Embeddings + LR baseline
#22
alecokas
closed
3 years ago
1
Update processing and stats
#21
alecokas
closed
3 years ago
0
Early stopping
#20
tyler-martin-12
closed
3 years ago
0
TD-IDF + Logistic regression model with training
#19
alecokas
closed
3 years ago
0
English Words Evaluation
#18
alecokas
closed
3 years ago
2
Sparse GAT
#17
alecokas
closed
3 years ago
0
Unidecode: Decode accent / strange non-ascii characters
#16
alecokas
closed
3 years ago
0
Improve steming map cleaning process
#15
alecokas
closed
3 years ago
0
CLI management
#14
alecokas
closed
3 years ago
0
Add index offset for the vocab size
#13
alecokas
closed
3 years ago
0
Updated stats notebook after redoing stemming for zenodo data
#12
tyler-martin-12
closed
3 years ago
0
Add missing data cleaning for Zenodo
#11
alecokas
closed
3 years ago
2
Summary stats notebook
#10
tyler-martin-12
closed
3 years ago
0
Added cleaning step to stemming pipeline
#9
tyler-martin-12
closed
3 years ago
0
Integrate stemming into tokenization
#8
alecokas
closed
3 years ago
1
Add helper function to generate cleaner stemming map
#7
alecokas
closed
3 years ago
0
Minor fixes on for download_stemming
#6
tyler-martin-12
closed
3 years ago
0
Swahili news data
#5
alecokas
closed
3 years ago
0
Download stemming data
#4
tyler-martin-12
closed
3 years ago
2
Add FastText and rename embedding directory
#3
alecokas
closed
3 years ago
0
added vocab count functionality
#2
tyler-martin-12
closed
3 years ago
0
Quick file structure refactor
#1
alecokas
closed
3 years ago
0