facebookresearch / Permutation-Equivariant-Seq2Seq
Humans understand novel sentences by composing meanings and roles of core language components. In contrast, neural network models for natural language modeling fail when such compositional generalization is required. The main contribution of this paper is to hypothesize that language compositionality is a form of group-equivariance. Based on thi…
☆27Updated 4 years ago
Related projects ⓘ
Alternatives and complementary repositories for Permutation-Equivariant-Seq2Seq
- PyTorch code for meta seq2seq learning☆43Updated 4 years ago
- Learning with latent language☆50Updated 3 years ago
- Measuring compositionality in representation learning☆71Updated 5 years ago
- Estimating Gradients for Discrete Random Variables by Sampling without Replacement☆39Updated 4 years ago
- Pytorch Implemetation for our NAACL2019 Paper "Riemannian Normalizing Flow on Variational Wasserstein Autoencoder for Text Modeling" http…☆62Updated 4 years ago
- LP-SparseMAP: Differentiable sparse structured prediction in coarse factor graphs☆41Updated last year
- Code for the publication Learning to Reason with Third-Order Tensor Products.☆39Updated 5 years ago
- An implementation of DIP-VAE from the paper "Variational Inference of Disentangled Latent Concepts from Unlabelled Observations" by Kumar…☆24Updated 6 years ago
- Systematic generalization test for CLEVR☆15Updated 4 years ago
- Dataset and documentation for paper on explaining solutions to physical reasoning tasks (ESPRIT))☆21Updated 3 years ago
- Official code repository of the paper Learning Associative Inference Using Fast Weight Memory by Schlag et al.☆26Updated 3 years ago
- Usable implementation of Emerging Symbol Binding Network (ESBN), in Pytorch☆23Updated 3 years ago
- Solving reinforcement learning tasks which require language and vision☆32Updated last year
- Code for "Systematic Generalization: What Is Required and Can It Be Learned"☆37Updated 5 years ago
- Low-variance and unbiased gradient for backpropagation through categorical random variables, with application in variational auto-encoder…☆17Updated 4 years ago
- ☆13Updated 3 years ago
- Active Imitation Learing with Noisy Guidance☆10Updated 4 years ago
- ☆26Updated 5 years ago
- ☆28Updated 2 years ago
- Tensor product decomposition network☆18Updated 3 years ago
- ☆24Updated 3 years ago
- Code for NAACL paper☆21Updated 6 years ago
- SparseMax activation function implementation (ICML 2016) (PyTorch)☆26Updated 6 years ago
- ☆42Updated 3 years ago
- ☆24Updated 6 months ago
- Open source implementation of SeaRNN (ICLR 2018, https://openreview.net/forum?id=HkUR_y-RZ)☆49Updated 6 years ago
- Cooperative Learning of Disjoint Syntax and Semantics☆49Updated 5 years ago
- Compositional generalization through meta sequence-to-sequence learning☆83Updated 4 years ago
- PhD thesis (updating) of Jiatao Gu from HKU☆19Updated 6 years ago