Difference between revisions of "讨论:2015-08-17"

@@ Line 1: / Line 1: @@
-Works in This week:
-.Finish training word embeddings via 5 models :
-using EnWiki dataset(953M):
-CBOW,Skip-Gram(SG)
-using text8 dataset(95.3M):
-CBOW,Skip-Gram(SG),C&W,GloVe,LBL and Order(count-based)
-.Use tasks to measure quality of the word vectors with various dimensions:
-word similarity(ws)
-the TOEFL set
-analogy task
-text classification
-named entity recognition(ner)
-sentence-level sentiment classification (based on convolutional neural networks),just call it 'cnn'
-part-of-speech tagging(pos)

Latest revision as of 04:53, 19 August 2015