sacmehta / PRULinks
Pyramidal Recurrent Units (PRUs): A New LSTM Unit
☆10Updated 6 years ago
Alternatives and similar repositories for PRU
Users that are interested in PRU are comparing it to the libraries listed below
Sorting:
- ☆14Updated 5 years ago
- Experimenting with Hierarchical Attention Networks from https://arxiv.org/abs/1606.02393 in Keras☆13Updated 8 years ago
- Deep neural models for core NLP tasks☆13Updated 7 years ago
- Highway networks implemented in PyTorch.☆55Updated 8 years ago
- Pytorch implementation of bytenet from "Neural Machine Translation in Linear Time" paper☆46Updated 7 years ago
- Auto-Encoding Variational Neural Machine Translation☆16Updated 5 years ago
- The Importance of Being Recurrent for Modeling Hierarchical Structure☆25Updated 6 years ago
- ☆12Updated 6 years ago
- An example of DyNet autobatching for the NIPS "how to code a paper" workshop☆12Updated 7 years ago
- ☆19Updated 8 years ago
- The training code for the EMNLP 2017 paper "Learning Generic Sentence Representations Using Convolutional Neural Networks"☆34Updated 7 years ago
- Re-implementation of Bi-Directional Block Self-Attention for Fast and Memory-Efficient Sequence Modeling (T. Shen et al., ICLR 2018) on P…☆42Updated 7 years ago
- Code for the EACL paper "Using the Output Embedding to Improve Language Models" by Ofir Press and Lior Wolf☆46Updated 7 years ago
- ☆49Updated 7 years ago
- Deep generative model for sentiment analysis☆34Updated 8 years ago
- Visual Bidirectional Kernelized Network for Visual Question Answering☆11Updated 7 years ago
- Implementing FastSent in theano☆12Updated 9 years ago
- A sentence encoding-based model for natural language inference☆31Updated 7 years ago
- Quasi-RNN for language modeling☆57Updated 8 years ago
- DyNet implementation of stack LSTM experiments by Grefenstette et al.☆21Updated 7 years ago
- ☆22Updated 8 years ago
- code for our IJCAI 2018 paper : "Lifelong Domain Word Embedding via Meta-Learning"☆11Updated 6 years ago
- Converts Quora's new NLU dataset to SNLI txt/jsonl format, plus test/dev split, tokenization.☆14Updated 8 years ago
- Code and dataset for "Transfer Learning Between Related Tasks Using Expected Label Proportions"☆16Updated 5 years ago
- A PyTorch implementation of Recurrent Additive Networks by Lee et al. (2017)☆29Updated 7 years ago
- Open source implementation of SeaRNN (ICLR 2018, https://openreview.net/forum?id=HkUR_y-RZ)☆48Updated 6 years ago
- PhD thesis (updating) of Jiatao Gu from HKU☆19Updated 6 years ago
- PyTorch study☆14Updated 7 years ago
- ☆28Updated 9 years ago
- Towards cross-lingual distributed representations without parallel text trained with adversarial autoencoders☆22Updated 8 years ago