structured-neural-summarization-replication icon indicating copy to clipboard operation
structured-neural-summarization-replication copied to clipboard

Published 20 hours ago • verified publisher icon emalgorithm
→

Metadata

Replication of the paper "Structured Neural Summarization" which uses Graph Neural Networks and Seq2Seq models to summarize natural language and source code.

Results 3 structured-neural-summarization-replication issues
Sort by recently updated
recently updated
newest added

Questions about the corpus proto files

I'm confused about the corpus proto files used in this project. Are they transformed by original AST JSON files?

WayneTseng123 avatar WayneTseng123

Documentation on requirements

It would be nice if the readme included a couple of lines on requirements, specially the cuda version that this code was ran with（I'm getting an error which I'm guessing...

shellycsy avatar shellycsy

Embeddings through ReLU an unconventional decision

This is not necessarily wrong, but I want to point out that using a ReLU [here](https://github.com/emalgorithm/structured-neural-summarization-replication/blob/b5b1883e2fbf32c65ac9d5813c6b260811c294cd/models/lstm_decoder.py#L18) is not a very common choice as far as I know. This might not...

mallamanis avatar mallamanis

← Metadata

21
Stars
3
Forks
Watchers

Owner

verified publisher icon emalgorithm

Metadata

Replication of the paper "Structured Neural Summarization" which uses Graph Neural Networks and Seq2Seq models to summarize natural language and source code.

Back