|GitHub – bloomberg/koan: A word2vec negative sampling implementation with correct CBOW update.
Although continuous bag of word (CBOW) embeddings can be trained more quickly than skipgram (SG) embeddings, it is a common belief that SG embeddings tend to perform better in practice. This was observed by the original authors of Word2Vec  and also in subsequent work . However, we found that …
- The Pile An 800GB Dataset of Diverse Text for Language Modeling
- DynaSent: Dynamic Sentiment Analysis Dataset