Data Augmentation for Improved Generalizability of Natural Language Processing Models

Name		Name	Last commit message	Last commit date
Latest commit History 191 Commits
aug_hard/hyperpartisan_news		aug_hard/hyperpartisan_news
aug_large		aug_large
aug_sorted		aug_sorted
aug_unlabeled		aug_unlabeled
baselines/full data		baselines/full data
data		data
docs		docs
emb		emb
failed_tests_by_base_models		failed_tests_by_base_models
perturb		perturb
s2_data		s2_data
s3_data		s3_data
same_label		same_label
src		src
stats		stats
task5a		task5a
.gitattributes		.gitattributes
02-acl-dense.ipynb		02-acl-dense.ipynb
02-acl-tfidf.ipynb		02-acl-tfidf.ipynb
02_acl_dense.txt		02_acl_dense.txt
02_acl_sparse.txt		02_acl_sparse.txt
04_hyper_dense.txt		04_hyper_dense.txt
04_hyper_sparse.txt		04_hyper_sparse.txt
07_imdb_dense.txt		07_imdb_dense.txt
07_imdb_sparse.txt		07_imdb_sparse.txt
README.md		README.md
create_new_train.py		create_new_train.py
main.py		main.py
perform_union.py		perform_union.py
perform_union_same_label.py		perform_union_same_label.py
run_me.sh		run_me.sh
same_label.py		same_label.py
union_check.py		union_check.py

Provide feedback