sequence input X = {[CLS], W, [SEP], C, [SEP], V }
source code C = {c1, c2, ..., cn}
comment W = {w1, w2, ..., wm}
where V = {v1, v2, ..., vk} is a set of variables
E = {ε1, ε2, ..., εl} is a set of direct edges that represent where the value of each variable comes from.
We use a special position embedding for all variables to indicate that they are nodes of data flow.
'미분류' 카테고리의 다른 글
Tokenizer은 어떻게 만들어졌는가? (0) | 2024.03.26 |
---|---|
huggingface의 AutoModel 클래스 (0) | 2024.03.20 |
훈련하면 훈련한거지 사전훈련은 또 뭔데 (0) | 2024.03.15 |
핸즈온 머신러닝 Ch 10 연습문제 (0) | 2024.03.12 |
딥러닝 관련 의문 (1) | 2024.03.08 |