word-embedding-dimensionality-selection

word-embedding-dimensionality-selection copied to clipboard

huabao97

word2vec CBOW

1

Thanks for sharing the code! Sorry if the question is silly - my understanding of word embeddings is still premature and lack the required math background: Should the SignalMatrix implementation...

ronhab

Error when executing in cmd

4

Hi, first thank you for making python implementation for your paper. When I executed package in cmd, I ran into an error. My environment is windows 10, 64 bit and...

bohyunshin

core dumped error

6

error message: Segmentation fault (core dumped) nohup python -m main --file data/train.txt --config_file config/train.yml --algorithm word2vec

shenxuhui

Noise estimation in signal_matrix.py

13

Line: self.noise = np.std(diff) * 0.5 seems to be inconsistent with Frobenius term used in paper: ||M1-M2||/(2sqrt(mn)). Instead it should be np.sum(diff**2)**(0.5)/(2*n)? Btw, isn't m=n=vocabulary size? Under this assumption, what's...

JamesTuna

does it use too much memory ?

12

cat config/word2vec_sample_config.yml skip_window: 5 neg_samples: 1 vocabulary_size: 100000 min_count: 100

ahhygx

Will this work on fasttext embeddings ?

3

A beautiful work by you. Hope to see similar work for other types of embeddings like contextual word embeddings. Will this work with fastext ? If no, what files I...

Priyansh2

about corpus format

4

I have a question about the format of corpus, I noticed the text8 corpus in data folder write in just one line, I want to know there is no influence...

OYE93