Mask-Align icon indicating copy to clipboard operation
Mask-Align copied to clipboard

Code for our paper "Mask-Align: Self-Supervised Neural Word Alignment" in ACL 2021

Results 7 Mask-Align issues
Sort by recently updated
recently updated
newest added

I can use your command to generate alignment based on bpe level. But how to generate alignment based on token level?

Did you apply bpe in your train data? What do you mean by "We used a joint source and target Byte Pair Encoding (BPE) (Sennrich et al., 2016) with 40k...

Hi, I'm trying to run the training script with Python 3.8.10 and `torch==1.10.2+cu113`, and I obtain the following error: ```shell >> bash thualign/bin/train.sh -s mask_align -e agree_deen running mask_align Traceback...

![training](https://user-images.githubusercontent.com/45490378/141267037-a7d4c324-dc55-40ff-9a7a-a257b972c69d.png) There is an error during the training when I used my training data. However, the training steps didn't stopped. Do you know what it's going on with it?

![config](https://user-images.githubusercontent.com/45490378/140895949-edc5e39e-158b-41bc-bf52-e8aba91bbbf0.png) ![tensorboard1](https://user-images.githubusercontent.com/45490378/140896572-d69a3086-75a1-485e-bf4d-fc812709ce83.png) I set eval_plot = True in my config file(example.config), but there is no images in the tensorboard when I finished the training step.

What does "9467" mean in the final test result: alignment-soft.txt: 14.4% (87.7%/83.5%/9467)?

I try to train a mask_align model with default config in the repo (only change data paths) and DE-EN training data from https://github.com/lilt/alignment-scripts. In some of training steps the losses...