Stelios Mathioulakis

Hello and thanks for sharing this. I have a question, do I need to download the datasets described [here ](https://github.com/open-mmlab/mmfashion/blob/master/docs/DATA_PREPARATION.md) in order to make predictions with new images or can...

Torch.save() for large training Dataset

1

Hello, I know this is not directly related to awesome-align, but I have a large training set of 10M source/target pairs and it takes 4 hours to process them before...

Inputs shoult be tokenized only for training/evaluation sets?

1

Hello, Your README states: > Inputs should be tokenized and each line is a source language sentence and its target language translation, separated by (|||). You can see some examples...

Is it possible to incorporate POS tag info to aid alignment?

1

Hello and many thanks for sharing the project I have an open question/discussion: would it be possible to incorporate the POS information of each token during training? For example, by...

Hello and thanks for sharing this. A question: can Lbl2Vec perform well when the "documents" are paragraph-sized? For example 3-5 sentences? Would we need to change Doc2Vec that Lbl2Vec currently...

Can I disable text validation?

4

Hello and thanks for the repo, I think I have an issue with text validation. I have created a folia Doc with sentence elements and their text. I am machine...