spcl/ncc
Neural Code Comprehension: A Learnable Representation of Code Semantics
Learns code semantics through `inst2vec`, an embedding space that represents LLVM IR statements and their surrounding context as a graph. Targets language-agnostic code understanding by converting source code to intermediate representation before training graph neural networks. Includes pre-trained embeddings and downstream task implementations for algorithm classification, device mapping prediction, and thread coarsening optimization—all using TensorFlow/Keras on the same unified architecture.
216 stars. No commits in the last 6 months.
Stars
216
Forks
50
Language
Python
License
BSD-3-Clause
Category
Last pushed
Nov 22, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/spcl/ncc"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
MilaNLProc/contextualized-topic-models
A python package to run contextualized topic modeling. CTMs combine contextualized embeddings...
vinid/cade
Compass-aligned Distributional Embeddings. Align embeddings from different corpora
ina-foss/twembeddings
Sentence embeddings for unsupervised event detection in the Twitter stream: study on English and...
criteo-research/CausE
Code for the Recsys 2018 paper entitled Causal Embeddings for Recommandation.
vintasoftware/entity-embed
PyTorch library for transforming entities like companies, products, etc. into vectors to support...