Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

是否考虑过将decoder部分的任务转换为预测词角标,而不是bpe index #14

Open
34127chi opened this issue Mar 7, 2022 · 1 comment

Comments

@34127chi
Copy link

34127chi commented Mar 7, 2022

以公开数据集合训练得到模型,接着在新的数据集上进行三元组任务(triplet)抽取,发现Invalid token的比例很大

是否有考虑过在encoder的embedding部分对词(word)进行编码,decoder部分的任务转换为预测词角标的,从而减少了invalid token的比例?

@yhcc
Copy link
Owner

yhcc commented May 25, 2022

这里主要是预训练模型不太能接受word的编码,非法的预测实际上可以在decode的时候进行限制的。需要修改一下decode时候的beam search算法。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants