Seungwoo Lee
Seungwoo Lee
Thank you for sharing your code and I am very interested in dice loss especially for NER task. Here you are sharing CoNLL2003 data of MRC format but the script...
I read [the ACL2020 paper](https://arxiv.org/pdf/1911.02855.pdf) and it suggests self-adjustment in the Dice Loss with Figure 1, which explains the derivative approaches zero right after p exceeds 0.5. This is the...
I modified followings: - add an option for selecting pre or post-padding - add mask support to ContextualizedEmbedding - modified forward/backward index input by removing rows (sentence indices) and using...