List your company
ResearchFormerly WizWand

Sentiment Classification on Elec

6.27Error Ratetv-embeddings
6.05247.52128.9910.4588Dec 1, 2014Dec 22, 2014Jan 12, 2015Feb 2, 2015Feb 23, 2015Mar 16, 2015Apr 6, 2015
Updated 8mo ago

Evaluation results

MethodLinks
tv-embeddingsExtra resource=Unlabeled data2015.046.27
seq2-bown-CNNvocabulary=30K most frequent words2014.127.14
CNN2015.047.14
seq2-CNNvocabulary=30K most frequent words2014.127.48
seq-CNNvocabulary=30K most frequent words2014.127.64
NB-LM bow3 (all)n-grams=3, vocabulary_size=all (up to 5M)2014.128.11
NB-LMFeatures=1-3grams2015.048.11
bow-CNNvocabulary=30K most frequent words2014.128.39
NN bow3 (all)n-grams=3, vocabulary_size=all (up to 5M)2014.128.48
dense NNFeatures=1-3grams2015.048.48
SVM bow3 (all)n-grams=3, vocabulary_size=all (up to 5M)2014.128.71
SVMFeatures=1-3grams2015.048.71
SVM bow2 (all)n-grams=2, vocabulary_size=all (up to 5M)2014.129.05
SVM bow3 (30K)n-grams=3, vocabulary_size=30K most frequent2014.129.16
SVM bow1 (all)n-grams=1, vocabulary_size=all (up to 5M)2014.1211.71