This folder contains examples for getting pretrained embedding vectors.
Word embedding is a technique to map words or phrases from a vocabulary to vectors or real numbers. The learned vector representations of words capture syntactic and semantic word relationships and therefore can be very useful for tasks like sentence similary, text classifcation, etc.
https://github.com/microsoft/nlp-recipes/blob/master/examples/embeddings/README.md
There is a survey article titled "学習済み日本語word2vecとその評価について". This article introduces many Japanese pretrained embedding models avaliable and evaluate them.
| Notebook | Environment | Description |
|---|---|---|
| Word2vec | Local | Get word2vec vectors pretrained by Japanese Wikipedia |
| fastText | Local | Get fastText vectors pretrained by Japanese Common Crawl |
| Download Pre-trained Embeddings | Local | Download pre-trained embeddings by chakin |
| Universal Sentence Encoder | Local | Get Universal Sentence Encoder |