Bug in augment_sentence function about tanl HOT 3 CLOSED

Thanks for pointing this out!

I re-wrote augment_sentence and expand_tokens indexing the nodes by integers (their positions in the augmentations list) instead of spans. The root is now -1. This implementation should be cleaner, as it clearly distinguishes between the root and an entity that spans the whole sentence.

from tanl.

Hi, you are right. Thanks for spotting the problem and providing a simple solution!

from tanl.

Hi,

I just found that my solution above is incomplete. There also have to be changes made in expand_tokens to recover the index from -1 to 0. To be more specific, I add

i = max(i, 0)

above line 39 and

start = max(start, 0)

before line 45 in utils.py.
I am sorry for not fully testing my solution before posting.

Best,
Xiang

from tanl.