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

AKT模型中的问题 #164

Open
zncj2fdx opened this issue Jan 11, 2024 · 1 comment
Open

AKT模型中的问题 #164

zncj2fdx opened this issue Jan 11, 2024 · 1 comment

Comments

@zncj2fdx
Copy link

您好,在AKT模型中,有这样几种嵌入
self.difficult_param = nn.Embedding(self.n_pid+1, 1) # 题目难度
self.q_embed_diff = nn.Embedding(self.n_question+1, embed_l) # question emb, 总结了包含当前question(concept)的problems(questions)的变化
self.q_embed = nn.Embedding(self.n_question, embed_l)

为什么前两种嵌入需要elf.n_pid+1和self.n_question+1。而第三种直接传入n_question

@sonyawong
Copy link
Collaborator

您好,在AKT模型中,有这样几种嵌入 self.difficult_param = nn.Embedding(self.n_pid+1, 1) # 题目难度 self.q_embed_diff = nn.Embedding(self.n_question+1, embed_l) # question emb, 总结了包含当前question(concept)的problems(questions)的变化 self.q_embed = nn.Embedding(self.n_question, embed_l)

为什么前两种嵌入需要elf.n_pid+1和self.n_question+1。而第三种直接传入n_question

self.n_pid代表的是题目ID的数量, self.n_question是知识点ID的数量, self.difficult_param代表原论文 rasch model-based emb中的$\mu_{q_t}$, self.q_embed_diff和self.q_embed分别是$\mathbf{d}{c_t}$和$\mathbf{c}{c_t}$, 所以用的是self.n_question. 具体可以查看原论文Section 3.4

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