1. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter;sanh;arXiv [cs CL],2019
2. Dependency-Based Word Embeddings
3. Adapt or get left behind: Domain adaptation through BERT language model finetuning for Aspect-Target Sentiment Classification;rietzler;arXiv [cs CL],2019
4. Efficient estimation of word representations in vector space;mikolov;arXiv [cs CL],2013
5. Multilabel Text Classification in News Articles Using Long-Term Memory with Word2Vec