“Ling Luo 2015-08-31”版本间的差异
来自cslt Wiki
(→Works in the past:) |
(→Works in this week:) |
||
第30行: | 第30行: | ||
word similarity: | word similarity: | ||
− | try to use different similarity calculation | + | try to use different similarity calculation methods |
named entity recognition | named entity recognition | ||
focus on cnn | focus on cnn |
2015年9月2日 (三) 02:22的版本
Works in the past:
1.Finish training word embeddings via 5 models :
using EnWiki dataset(953M):
CBOW,Skip-Gram
using text8 dataset(95.3M):
CBOW,Skip-Gram,C&W,GloVe,LBL and Order(count-based)
2.Use tasks to measure quality of the word vectors with various dimensions(10~200):
word similarity
the TOEFL set:small dataset
analogy task:9K semantic and 10.5K syntactic analogy questions
text classification:IMDB dataset——pos&neg,use unlabeled dataset to train word embeddings
sentence-level sentiment classification (based on convolutional neural networks)
part-of-speech tagging
Works in this week:
word similarity: try to use different similarity calculation methods
named entity recognition
focus on cnn