ziyin-dl / word-embedding-dimensionality-selection

On the Dimensionality of Word Embedding
https://nips.cc/Conferences/2018/Schedule?showEvent=12567
MIT License
329 stars 44 forks source link

Tokenizer code ignores vocabulary size parameter from the config file #7

Closed shudima closed 5 years ago

shudima commented 5 years ago

When specifying the vocabulary size in the yaml config, the code uses the default 10,000

I created this PR to fix the issue https://github.com/ziyin-dl/word-embedding-dimensionality-selection/pull/6

ziyin-dl commented 5 years ago

Acknowledged, thanks.