soskek / efficient_softmaxLinks
BlackOut and Adaptive Softmax for language models by Chainer
☆11Updated 7 years ago
Alternatives and similar repositories for efficient_softmax
Users that are interested in efficient_softmax are comparing it to the libraries listed below
Sorting:
- Implementation of "Controlling Output Length in Neural Encoder-Decoders"☆42Updated 7 years ago
- BiLSTM-CRF for sequence labeling in Dynet☆80Updated 8 years ago
- Collection of Evaluation Metrics and Algorithms for Machine Translation☆76Updated 7 years ago
- ☆46Updated 7 years ago
- Implementation of A Structured Self-attentive Sentence Embedding☆108Updated 6 years ago
- ☆28Updated 9 years ago
- Decomposable Attention Model for Sentence Pair Classification (from https://arxiv.org/abs/1606.01933)☆95Updated 8 years ago
- Evaluation tool for word embeddings☆27Updated 9 years ago
- implementation of SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient☆33Updated 8 years ago
- fairseq: Convolutional Sequence to Sequence Learning (Gehring et al. 2017) by Chainer☆67Updated 8 years ago
- Unofficial implementation algorithms of attention models on SNLI dataset☆33Updated 7 years ago
- modlm: A toolkit for mixture of distributions language models☆27Updated 7 years ago
- sequence to sequence neural network model for dialogue system☆44Updated 9 years ago
- This is a repo for multiNLI_encoder.☆58Updated 7 years ago
- Gaussian Mixture Latent Vector Grammars☆30Updated 6 years ago
- Aspect-augmented Adversarial Networks for Domain Adaptation☆49Updated 8 years ago
- ☆13Updated 7 years ago
- Hierarchical encoder-decoder framework for sequences of words, sentences, paragraphs and documents using LSTM and GRU in Theano☆108Updated 8 years ago
- ☆53Updated 8 years ago
- ☆55Updated 9 years ago
- Dependency tree-based RNN☆32Updated 9 years ago
- Implementation in Tensorflow of A Structured Self-attentive Sentence Embedding with the sentiment analysis task.☆66Updated 8 years ago
- Implementing , learning and re implementing "End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF" in keras☆71Updated 7 years ago
- Learning Word Representations by Jointly Modeling Syntagmatic and Paradigmatic Relations (ACL2015)☆28Updated 9 years ago
- ☆124Updated 8 years ago
- ☆59Updated 9 years ago
- A latent variable RNN model for discourse-driven language modeling☆36Updated 9 years ago
- Code for paper "End-to-End Non-Factoid Question Answering with an Interactive Visualization of Neural Attention Weights"☆65Updated 7 years ago
- CRFsuite with partial annotation. Used in our paper 'Domain adaptation for CRF-based Chinese word segmentation using free annotations'☆44Updated 9 years ago
- Chinese word segmentation model with word-based character embeddings.☆12Updated 7 years ago