Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking.
Michael Sejr SchlichtkrullNicola De CaoIvan TitovPublished in: ICLR (2021)
Keyphrases
- neural network
- weighted graph
- undirected graph
- natural language processing
- disjoint paths
- graph structure
- pattern recognition
- graph model
- artificial neural networks
- edge information
- text mining
- fuzzy logic
- objective function
- graph based algorithm
- directed graph
- back propagation
- question answering
- genetic algorithm
- artificial intelligence
- graph representation
- graph theoretic
- edge weights
- natural language
- shortest path
- multi layer
- graph theory
- neural nets
- multilayer perceptron
- feed forward
- neural network model
- information extraction
- activation function
- structured data
- connected components
- graph mining
- directed acyclic graph
- free text
- edge detector
- machine translation
- fault diagnosis
- random walk
- scale space
- image processing
- social networks
- machine learning