Stars
Type-and-example directed program synthesis using example propagation, as described in Program Synthesis Using Example Propagation.
Repository of an Archi plugin that enables Knowledge Graph based anaylsis of ArchiMate models.
This platform enables the automated transformation of conceptual models created with EMF, Papyrus, or ADOxx into a Knowledge Graph which can be represented by GraphML, RDF, and OWL2.
Entity Relationship Diagram modeling tool realized as a language server that is distributed as a VS Code extension.
This is the official code for the paper CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning (NeurIPS22).
KG-BART: Knowledge Graph-Augmented BART for GenerativeCommonsense Reasoning
Extracting action sequences and generating domain models.
Code for ACL'2021 paper WARP 🌀 Word-level Adversarial ReProgramming. Outperforming `GPT-3` on SuperGLUE Few-Shot text classification. https://aclanthology.org/2021.acl-long.381/
[EMNLP'21] Plan-then-Generate: Controlled Data-to-Text Generation via Planning
[Tool] For Knowledge Graph Representation Learning
Code for TACL 2022 paper on Data-to-text Generation with Variational Sequential Planning
Exercises for the Analysis of Knowledge Graphs
PyTorch code for NAACL 2022 paper: DialoKG: Knowledge-Structure Aware Task-Oriented Dialogue Generation (https://aclanthology.org/2022.findings-naacl.195/).
CodeGen is a family of open-source model for program synthesis. Trained on TPU-v4. Competitive with OpenAI Codex.
Source code of PyGAD, a Python 3 library for building the genetic algorithm and training machine learning algorithms (Keras & PyTorch).
Pretrained Language Models for Source code
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021.
A Python package for manipulating atomistic data of software in computational science