facebookresearch / Permutation-Equivariant-Seq2SeqLinks
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 5 years ago
Alternatives and similar repositories for Permutation-Equivariant-Seq2Seq
Users that are interested in Permutation-Equivariant-Seq2Seq are comparing it to the libraries listed below
Sorting:
- Estimating Gradients for Discrete Random Variables by Sampling without Replacement☆40Updated 5 years ago
- Usable implementation of Emerging Symbol Binding Network (ESBN), in Pytorch☆25Updated 4 years ago
- ☆41Updated 4 years ago
- Compositional generalization through meta sequence-to-sequence learning☆83Updated 5 years ago
- The official repository for our paper "The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers". We s…☆67Updated 2 years ago
- LP-SparseMAP: Differentiable sparse structured prediction in coarse factor graphs☆41Updated last year
- PyTorch code for meta seq2seq learning☆43Updated 5 years ago
- Pytorch Implemetation for our NAACL2019 Paper "Riemannian Normalizing Flow on Variational Wasserstein Autoencoder for Text Modeling" http…☆63Updated 5 years ago
- ☆25Updated last year
- Learning with latent language☆51Updated 4 years ago
- Official code repository of the paper Learning Associative Inference Using Fast Weight Memory by Schlag et al.☆28Updated 4 years ago
- Measuring compositionality in representation learning☆73Updated 6 years ago
- ☆50Updated 4 years ago
- ☆24Updated 3 months ago
- Systematic generalization test for CLEVR☆15Updated 5 years ago
- Suite of 500 procedurally-generated NLP tasks to study language model adaptability☆21Updated 3 years ago
- Code publication to the paper "Normalized Attention Without Probability Cage"☆16Updated 3 years ago
- Cooperative Learning of Disjoint Syntax and Semantics☆50Updated 6 years ago
- ReaSCAN is a synthetic navigation task that requires models to reason about surroundings over syntactically difficult languages. (NeurIPS…☆20Updated 3 years ago
- Code for gradient rollback, which explains predictions of neural matrix factorization models, as for example used for knowledge base comp…☆21Updated 4 years ago
- ☆50Updated 3 years ago
- ☆64Updated 5 years ago
- [ICLR 2020] FSPool: Learning Set Representations with Featurewise Sort Pooling☆42Updated last year
- Language Model Baselines for PyTorch☆41Updated 5 years ago
- Low-variance and unbiased gradient for backpropagation through categorical random variables, with application in variational auto-encoder…☆17Updated 5 years ago
- An implementation of DIP-VAE from the paper "Variational Inference of Disentangled Latent Concepts from Unlabelled Observations" by Kumar…☆26Updated 7 years ago
- Implementation of Stochastic Beam Search using Fairseq☆105Updated 6 years ago
- The server portion of the Neural Chat project to deploy chatbots on web. This code is accompanied by another repository that includes the…☆36Updated 4 years ago
- [AAAI 2020 Oral] Low-variance Black-box Gradient Estimates for the Plackett-Luce Distribution☆38Updated 4 years ago
- Factorization of the neural parameter space for zero-shot multi-lingual and multi-task transfer☆39Updated 4 years ago