Disentangling Generative Factors in Natural Language with Discrete Variational Autoencoders.
Giangiacomo MercataliAndré FreitasPublished in: CoRR (2021)
Keyphrases
- natural language
- factors that influence
- generative model
- natural language generation
- image segmentation
- data driven
- denoising
- discrete geometry
- machine learning
- factors influencing
- semantic interpretation
- question answering
- information extraction
- discrete version
- natural language processing
- knowledge representation
- natural language interface
- semantic analysis
- semantic representation
- data sets
- methods in computer vision
- key factors
- variational methods
- factors affecting
- finite number
- message passing
- probabilistic model
- optical flow
- image processing
- computer vision