QuickThoughts

Pytorch reimplementation of quickthoughts paper: https://arxiv.org/pdf/1803.02893.pdf. I've refactored code from original pytorch implementation.

Changes

I've refactored original code a bit. Made Learner class for simpler model creation. Support for sentencepiece tokenizer.

download data and clean it (lowercase, add space between punctuation)
change path to the training data file in conf (conf/conf_dev.py key data_path)
if you want to evaluate during training on some downstream task (like classification), do following:
- download downstream dataset, clean it like training data)
- change script in src_custom/eval.py, especially in load_encode_data function so that it knows how to load your dataset. You have to gie it a name
- add the name of your dataset to your conf (conf/conf_dev.py) in the key downstream_eval_datasets (you can add multiple downstream tasks, just make sure you add them to the conf and load_encode_data knows how to read in the data). During training downstream performance is saved/displayed
if you want to use sentencepiece tokenizer, add path to the model in the conf file
train model (example script train_dev.py or if you want to train from checkpoint train_dev_from_checkpoint.py)

If you wan to use model, use script get_vectors_dev.py as an example