“Ling Luo 2015-08-31”版本间的差异
来自cslt Wiki
（→Works in this week:） |
（→Works in the past:） |
||
| 第4行： | 第4行： | ||
1.''Finish training word embeddings via 5 models :'' | 1.''Finish training word embeddings via 5 models :'' | ||
| + | |||
using EnWiki dataset(953M): | using EnWiki dataset(953M): | ||
| + | |||
CBOW,Skip-Gram | CBOW,Skip-Gram | ||
| + | |||
using text8 dataset(95.3M): | using text8 dataset(95.3M): | ||
| + | |||
CBOW,Skip-Gram,C&W,GloVe,LBL and Order(count-based) | 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):'' | 2.''Use tasks to measure quality of the word vectors with various dimensions(10~200):'' | ||
| + | |||
word similarity(ws) | word similarity(ws) | ||
| + | |||
the TOEFL set:small dataset | the TOEFL set:small dataset | ||
| + | |||
analogy task:9K semantic and 10.5K syntactic analogy questions | analogy task:9K semantic and 10.5K syntactic analogy questions | ||
| + | |||
text classification:IMDB dataset——pos&neg,use unlabeled dataset to train word embeddings | text classification:IMDB dataset——pos&neg,use unlabeled dataset to train word embeddings | ||
| + | |||
sentence-level sentiment classification (based on convolutional neural networks) | sentence-level sentiment classification (based on convolutional neural networks) | ||
| − | |||
| + | part-of-speech tagging | ||
== Works in this week: == | == Works in this week: == | ||
2015年9月2日 (三) 02:19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(ws)
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(ws): try to use different similarity calculation method
named entity recognition(ner)
focus on cnn
