zysszy TreeGen issues - Githubissues

zysszy / TreeGen

A Tree-Based Transformer Architecture for Code Generation. (AAAI'20)

MIT License

90 stars 27 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

关于项目的运行

#27 Dyer233 closed 2 years ago
1
我实在忍不住吐槽一句#I couldn't help wanting to talk

#26 Smithol closed 2 years ago
3
Is TreeGen better than regular transformers?

#25 brando90 opened 2 years ago
1
Which tensorflow version to make the code work?

#24 bdqnghi opened 2 years ago
1
What does W_c[c1; ...; cM] notation in the paper mean for character embeddings?

#23 brando90 opened 2 years ago
3
Do you use CSTs or ASTs?

#22 brando90 opened 2 years ago
5
vocabulary 的疑惑

#21 boyang9602 opened 3 years ago
1
nlnum和copylst文件的含义

#20 boyang9602 opened 3 years ago
1
Why was TreeGen not trained with the standard warm up scheduler for Transformers?

#19 brando90 opened 3 years ago
5
resolve_data.py可能存在的问题和一些疑惑

#18 boyang9602 opened 3 years ago
4
Are the depth embedding used at every transformer block of TreeGen or only at the input?

#17 brando90 opened 3 years ago
1
How is the query vector masked and shifted so that the model does not cheat when predicting grammar rules?

#16 brando90 opened 3 years ago
4
How are general identifiers predicting e.g. functions from an available library? (besides the NL pointer net)

#15 brando90 opened 3 years ago
1
How is the target vector (program rules sequence) in TreeGen created during training?

#14 brando90 opened 3 years ago
1
What is missing from the repo?

#13 brando90 opened 3 years ago
1
Why use depth encoding in AST reader but not in query?

#12 brando90 opened 3 years ago
1
Are the programs that TreeGen generate guaranteed to be syntactically correct?

#11 brando90 opened 3 years ago
6
Why use WordConv (separable convolution) in NL encoder and not the usual Feedforward NN (like original transformer)?

#10 brando90 opened 3 years ago
7
predict_HS-B.py 中的处理流程，和"J_*"形式的方法的大致情况

#9 yueml opened 3 years ago
1
train_trans.txt和train_tree.txt里面数据含义和作用是什么

#8 yueml opened 3 years ago
8
data generation scripts

#7 lifengjin opened 3 years ago
2
ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()

#6 iamxpy closed 3 years ago
2
Need help to understand the code

#5 iamxpy opened 4 years ago
17
Error while training

#4 talk2kabir opened 4 years ago
4
How does decoder select the expanding path?

#3 ChengFu0118 opened 4 years ago
3
关于项目的运行

#2 17385 opened 4 years ago
7
LICENSE

#1 juancamilog closed 4 years ago
2