david-lee-1990 Goto Github PK

ggnn.pytorch

A PyTorch Implementation of Gated Graph Sequence Neural Networks (GGNN)

google-research

Google Research

graph-lstm

LSTM implementation, and multi-layer LSTMs for learning on graph neighborhoods

graph_nets

Build Graph Nets in Tensorflow

hgcn

Hyperbolic Graph Convolutional Networks in PyTorch.

hyte

EMNLP 2018: HyTE: Hyperplane-based Temporally aware Knowledge Graph Embedding

iepy

Information Extraction in Python

jieba

结巴中文分词

kb2e

Knowledge Graph Embeddings including TransE, TransH, TransR and PTransE

kglib

Grakn Knowledge Graph Library (ML R&D)

kid

Knowledge Infused Decoding

krlpapers

Must-read papers on knowledge representation learning (KRL) / knowledge embedding (KE)

learn_dl

Deep learning algorithms source code for beginners

mapleai

AI各领域学习资料整理。（A collection of all skills and knowledges should be got command of to obtain an AI relevant job offer. There are online blogs, my personal blogs, electronic books copy.）

metaicl

An original implementation of "MetaICL Learning to Learn In Context" by Sewon Min, Mike Lewis, Luke Zettlemoyer and Hannaneh Hajishirzi

minerva

Meandering In Networks of Entities to Reach Verisimilar Answers

ml-from-scratch

Machine Learning From Scratch. Bare bones Python implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from data mining to deep learning.

modular_rl

Implementation of TRPO and related algorithms

moran_v2

MORAN: A Multi-Object Rectified Attention Network for Scene Text Recognition

mtcnn-tensorflow

Reproduce MTCNN using Tensorflow

multihopkg

Multi-hop knowledge graph reasoning learned via policy gradient with reward shaping and action dropout

nq_bert-dm

onlineclusteringofbandits

openkp

Automatically extracting keyphrases that are salient to the document meanings is an essential step to semantic document understanding. An effective keyphrase extraction (KPE) system can benefit a wide range of natural language processing and information retrieval tasks. Recent neural methods formulate the task as a document-to-keyphrase sequence-to-sequence task. These seq2seq learning models have shown promising results compared to previous KPE systems The recent progress in neural KPE is mostly observed in documents originating from the scientific domain. In real-world scenarios, most potential applications of KPE deal with diverse documents originating from sparse sources. These documents are unlikely to include the structure, prose and be as well written as scientific papers. They often include a much diverse document structure and reside in various domains whose contents target much wider audiences than scientists. To encourage the research community to develop a powerful neural model with key phrase extraction on open domains we have created OpenKP: a dataset of over 150,000 documents with the most relevant keyphrases generated by expert annotation.

path-ranking-algorithm

Implement the Path ranking algorithm by python

powerful-gnns

How Powerful are Graph Neural Networks?

psl

The PSL software from the University of Maryland and the University of California Santa Cruz

psl-examples

Various examples to showcase the functionality of PSL.

pslqa

An implementation of Probabilistic Soft Logic Engine using Python/Gurobi

publaynet