# Pretrained Vector

- List on [DataServer](http://dev-reasoning-qa-data-ncl.nfra.io:7778/)

## English

- `Counter Fitting`: [Counter-fitting Word Vectors to Linguistic Constraints](http://mi.eng.cam.ac.uk/~nm480/naaclhlt2016.pdf)
    - counter\_fitted\_glove.300d.txt
 - `Cove`: [Learned in Translation: Contextualized Word Vectors (McCann et. al. 2017)](https://github.com/salesforce/cove)
     - wmtlstm-b142a7f2.pth
- `fastText`: [Enriching Word Vectors with Subword Information](https://github.com/facebookresearch/fastText)
    - fasttext.wiki.en.300d.txt
 - `GloVe`: [GloVe: Global Vectors for Word Representation](https://nlp.stanford.edu/projects/glove/)
     - glove.6B.50d.txt
     - glove.6B.100d.txt
     - glove.6B.200d.txt
     - glove.6B.300d.txt
     - glove.840B.300d.txt
 - `ELMo`: [Deep contextualized word representations](https://github.com/allenai/allennlp/blob/master/allennlp/modules/elmo.py)
     - elmo\_2x4096\_512\_2048cnn\_2xhighway\_weights.hdf5
     - elmo\_2x4096\_512\_2048cnn\_2xhighway\_options
- `Word2Vec`: [Distributed Representations of Words and Phrases and their Compositionality](https://code.google.com/archive/p/word2vec/)
    - GoogleNews-vectors-negative300.txt


## Korean

- `fastText`: [Enriching Word Vectors with Subword Information](https://github.com/facebookresearch/fastText)
    - fasttext.wiki.ko.300d.txt