Python scripts for training/testing paragraph vectors
Apache License 2.0
640
stars
191
forks
source link
Can the format/extension of Pre-trained word embeddings be '.bin' refrenced in this line https://github.com/jhlau/doc2vec/blob/158df84b83c1b2b3038c420df03a3f063f7a50be/train_model.py#L17 #31
amitjslearn
commented
4 years ago
Please, help me here. Should the format/extension of Pre-trained word embeddings in the below line always be '.txt' https://github.com/jhlau/doc2vec/blob/158df84b83c1b2b3038c420df03a3f063f7a50be/train_model.py#L17 I want to use the Associated Press News DBOW (0.6GB) as the pretrained_emb and further fine-tune it for my corpus. How would I do it? I am thinking of using the doc2vec.bin file in the Associated Press News DBOW (0.6GB), will it work?