vid-koci/bert-commonsense
Code for papers "A Surprisingly Robust Trick for Winograd Schema Challenge" and "WikiCREM: A Large Unsupervised Corpus for Coreference Resolution"
Python
Issues
- 1
- 8
two bugs in the code
#1 opened by YeDeming - 0
- 2
Hello, thank you for your interest. Train data, too, is processed in a way so that the first candidate is always the correct one. Note that the model is agnostic to the fact whether a candidate is the first or the second candidate, it simply assigns the current candidate a score without access to the other candidate (or the knowledge whether it's dealing with the first or the second candidate). The order in which the candidates are processed thus does not make any difference.
#4 opened by jc-ryan - 2
Possible bug
#3 opened by jc-ryan - 3