bfsujason

The following steps works for me (Windows 10): 1. Use command line to change to the path your/path/to/python/site-packages/backend 2. Run doccano init

Thank you for your reply. Yes, I have experience in English-Chinese translations in the field of corpus linguistics and computational linguistics. I think I'm able to handle the localization task...

max_align is the maximum alignment types such as 1:1, 1:2, etc. 5 means the alignments allowed are 1:0, 0:1, 1:1, 1:2, 2:1, 2:2, 2:3, and 3:2. You can set this...

I'm not sure whether removing punctuations could imporove the accuracy. It's very easy to give it a try though: just change the code in aligner.py and replace puctuations in the...

I updated requirements.txt to use the latest version of sentence-transformers. That seems to be working on Colab.

I think it's much easier to align every two languages first, then merge the alignments using some graph searching algorithm such as [connected component](https://networkx.org/documentation/stable/reference/algorithms/generated/networkx.algorithms.components.connected_components.html) For example, with one source text...

Is windsurf an AI-powered IDE? That is a good idea. You can ask AI how to align more than 2 languages using graph algorithm. I think it will solve your...

Thank you for your interest in Bertalign! The LaBSE model supports over 100 languages. However, Bertalign relies on [sentence-splitter](https://github.com/mediacloud/sentence-splitter) for sentence segmentation, which currently supports only 25 languages. If you...