Name		Name	Last commit message	Last commit date
Latest commit History 98 Commits
__pycache__		__pycache__
prod		prod
.gitignore		.gitignore
Clas with KFold.ipynb		Clas with KFold.ipynb
Ensemble 100 Regr models BigDrop 0610.ipynb		Ensemble 100 Regr models BigDrop 0610.ipynb
Ensemble 100 models more LM train top Quartile F1 0610.ipynb		Ensemble 100 models more LM train top Quartile F1 0610.ipynb
Ensemble 199 models.ipynb		Ensemble 199 models.ipynb
Ensemble 200 Regr models.ipynb		Ensemble 200 Regr models.ipynb
Ensemble 200 models more LM train top Quartile F1 ens BWD.ipynb		Ensemble 200 models more LM train top Quartile F1 ens BWD.ipynb
Ensemble 200 models more LM train top Quartile F1 ens Unigram BigDrop.ipynb		Ensemble 200 models more LM train top Quartile F1 ens Unigram BigDrop.ipynb
Ensemble 200 models more LM train.ipynb		Ensemble 200 models more LM train.ipynb
Ensemble 5 fold First Seed Regr models Big Drop LM.ipynb		Ensemble 5 fold First Seed Regr models Big Drop LM.ipynb
Ensemble 5 fold more LM train top Quartile F1.ipynb		Ensemble 5 fold more LM train top Quartile F1.ipynb
Finetune LM.ipynb		Finetune LM.ipynb
Grad Unfreeze Example.ipynb		Grad Unfreeze Example.ipynb
LM Train in notebook.ipynb		LM Train in notebook.ipynb
NLP Mixup After Embeddings Regr.ipynb		NLP Mixup After Embeddings Regr.ipynb
NLP Mixup After Embeddings.ipynb		NLP Mixup After Embeddings.ipynb
NMT_00.ipynb		NMT_00.ipynb
NMT_01.ipynb		NMT_01.ipynb
NMT_01b.ipynb		NMT_01b.ipynb
NMT_02.ipynb		NMT_02.ipynb
NMT_02a.ipynb		NMT_02a.ipynb
NMT_02a1_and.ipynb		NMT_02a1_and.ipynb
NMT_02a2 combine OR.ipynb		NMT_02a2 combine OR.ipynb
README.md		README.md
Single Model Sub.ipynb		Single Model Sub.ipynb
Tweets_Spanish_SP_LM_more_rules_QRNN.ipynb		Tweets_Spanish_SP_LM_more_rules_QRNN.ipynb
Tweets_Spanish_SP_LM_more_rules_QRNN_Labelsmoothing.ipynb		Tweets_Spanish_SP_LM_more_rules_QRNN_Labelsmoothing.ipynb
Tweets_Spanish_SP_LM_more_rules_RNN.ipynb		Tweets_Spanish_SP_LM_more_rules_RNN.ipynb
Tweets_Spanish_SP_LM_more_rules_RNN_Labelsmoothing_vocab15k.ipynb		Tweets_Spanish_SP_LM_more_rules_RNN_Labelsmoothing_vocab15k.ipynb
Tweets_Spanish_SP_LM_more_rules_Transformer.ipynb		Tweets_Spanish_SP_LM_more_rules_Transformer.ipynb
UpdateClasSubmission.ipynb		UpdateClasSubmission.ipynb
by_seed_bwd_perf		by_seed_bwd_perf
by_seed_fwd_perf		by_seed_fwd_perf
by_seed_reg_perf		by_seed_reg_perf
environment.yml		environment.yml
sp_tok.py		sp_tok.py
spanish_joke_classifier_NBSVM_baseline.ipynb		spanish_joke_classifier_NBSVM_baseline.ipynb
spanish_joke_classifier_tweet_only_LM_QRNN-LabelSmoothing[LM and Clas]-2018_data.ipynb		spanish_joke_classifier_tweet_only_LM_QRNN-LabelSmoothing[LM and Clas]-2018_data.ipynb
spanish_joke_classifier_tweet_only_LM_QRNN-LabelSmoothing[LM and Clas]-Copy1.ipynb		spanish_joke_classifier_tweet_only_LM_QRNN-LabelSmoothing[LM and Clas]-Copy1.ipynb
spanish_joke_classifier_tweet_only_LM_QRNN-LabelSmoothing[LM and Clas]-Regression.ipynb		spanish_joke_classifier_tweet_only_LM_QRNN-LabelSmoothing[LM and Clas]-Regression.ipynb
spanish_joke_classifier_tweet_only_LM_QRNN-LabelSmoothing[LM and Clas]-submission.ipynb		spanish_joke_classifier_tweet_only_LM_QRNN-LabelSmoothing[LM and Clas]-submission.ipynb
spanish_joke_classifier_tweet_only_LM_QRNN-LabelSmoothing[LM and Clas].ipynb		spanish_joke_classifier_tweet_only_LM_QRNN-LabelSmoothing[LM and Clas].ipynb
spanish_joke_classifier_tweet_only_LM_QRNN-LabelSmoothing[LM and Clas]_0607.ipynb		spanish_joke_classifier_tweet_only_LM_QRNN-LabelSmoothing[LM and Clas]_0607.ipynb
spanish_joke_classifier_tweet_only_LM_QRNN.ipynb		spanish_joke_classifier_tweet_only_LM_QRNN.ipynb
spanish_joke_classifier_tweet_only_LM_RNN-LabelSmoothing-15k.ipynb		spanish_joke_classifier_tweet_only_LM_RNN-LabelSmoothing-15k.ipynb
spanish_joke_classifier_tweet_only_LM_RNN-LabelSmoothing.ipynb		spanish_joke_classifier_tweet_only_LM_RNN-LabelSmoothing.ipynb
spanish_joke_classifier_tweet_only_LM_RNN.ipynb		spanish_joke_classifier_tweet_only_LM_RNN.ipynb
spanish_joke_classifier_tweet_only_LM_RNN_AttnHead.ipynb		spanish_joke_classifier_tweet_only_LM_RNN_AttnHead.ipynb
spanish_joke_classifier_tweet_only_LM_Transformer.ipynb		spanish_joke_classifier_tweet_only_LM_Transformer.ipynb

Repository files navigation

haha_2019

Using Fastai library to classify Twitter jokes in Spanish

Requires install of Fast.ai library for the Language Model and classification tasks

Data is installed in the same directory in ./data/ directory (but not checked into this repo.)
Start with the NBSVM as a baseline for classification. It has been run over several random splits and there is a plot showing the predicted values depending on the split. Mean accuracy is about 84% (but you could get as good as nearly 85% if you are lucky!)

Deep Learning Models

Using Sentencepiece for sub-word units and better vocab coverage.
SP ouputs .model and .vocab files in the current directory (I added to .gitignore)

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Repository files navigation

haha_2019

About

Releases

Packages

Languages

bfarzin/haha_2019

Folders and files

Latest commit

History

Repository files navigation

haha_2019

About

Resources

Stars

Watchers

Forks

Releases

Packages 0

Languages

Packages