-
More dimensions are better in correlation with human-rated word similarity
- Eigen-Expression Extraction should not be too high
-
Sentiment should be higher.
-
Narrower window is better for parsing Guidelines for determining the optimal number of dimensions for word distributed representations - Qiita
This page is auto-translated from /nishio/分散表現の次元 using DeepL. If you looks something interesting but the auto-translated English is not good enough to understand it, feel free to let me know at @nishio_en. I’m very happy to spread my thought to non-Japanese readers.