Giters

lipiji / TtT

code for ACL2021 paper "Tail-to-Tail Non-Autoregressive Sequence Prediction for Chinese Grammatical Error Correction"

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Clarifications

aksh555 opened this issue · comments

commented

Thanks for releasing the code. I have few questions:

  1. Why has the tagset been restricted to have only E and R labels reference, what about D and I and how is paraphrasing (swaps) being addressed?
  2. How is the VarLen scenario being handled? Would you be releasing scripts and data in future?
  3. How are the characters to be inserted for operations like insert being predicted?