Open karanchahal opened 6 years ago
Ive never tried, but it has been claimed on some paper that pretrained word vectors don't help much.
Transfer learning in NLP doesn't seem to have the same impact as that of images it seems like. Any good papers for transferring knowledge of pretrained nlp systems you recommend ?
Hi I'm making my own version if a image captioning model, I haven't gone through your code in detail yet. I was wondering if you have used pre-trained word vectors for this task or just used an one hot encoding representation ? And do you think the use of pre-trained word vectors make a substantial impact on training time and accuracy ?