Word segmentation for Thai

Word segmentation is mostly working quite well for Thai at the moment, but obviously there are some mistakes (for those who are not aware, there are no spaces between words in Thai). Since many of the mistakes are recurring ones (especially for a particular TV series), would it be possible for the user to make corrections to word boundaries in the future? Or would that be a huge project?

Also, this is a long shot, but I would do anything to be able to run the dictionary look-up on regular texts. Something similar to LingQ (they don’t offer Thai). Any chance that this is something you would ever do?

Thank you for an amazing extension! You have revolutionized the way I learn languages and the subscription is well worth the price.

1 Like

I’m having the same segmentation issue in Japanese:

I’ve seen wrong readings as well. I’ll be sure to cite some when I encounter them again.

Anyone else encountered this?