CyberZHG / keras-transformer-xl
Transformer-XL with checkpoint loader
☆68Updated 2 years ago
Related projects: ⓘ
- Position embedding layers in Keras☆60Updated 2 years ago
- Ordered Neurons LSTM☆30Updated 2 years ago
- BertQA - Attention on Steroids☆115Updated last year
- Comparing Text Classification results using BERT embedding and ULMFIT embedding☆65Updated 5 years ago
- BERT Extension in TensorFlow☆30Updated 5 years ago
- Reproducing Character-Level-Language-Modeling with Deeper Self-Attention in PyTorch☆59Updated 5 years ago
- Simple Tensorflow Implementation of "A Structured Self-attentive Sentence Embedding" (ICLR 2017)☆92Updated 6 years ago
- Reproducing Densely Interactive Inference Network in Keras☆74Updated 6 years ago
- Efficient Transformers for research, PyTorch and Tensorflow using Locality Sensitive Hashing☆93Updated 4 years ago
- Concatenate word and character embeddings in Keras☆44Updated 2 years ago
- An Attention Layer in Keras☆43Updated 5 years ago
- Adaptive embedding and softmax☆17Updated 2 years ago
- Re-implementation of ELMo on Keras☆135Updated last year
- A simple Keras implementation of Paper "Text Matching as Image Recognition"☆28Updated last year
- ☆40Updated this week
- Layer normalization implemented in Keras☆60Updated 2 years ago
- QANet in keras (with Cove)☆66Updated 5 years ago
- ☆64Updated this week
- attention block for keras Functional Model with only tensorflow backend☆26Updated 5 years ago
- add BERT to encoder part for https://github.com/memray/seq2seq-keyphrase-pytorch☆80Updated 5 years ago
- An Open-source Neural Hierarchical Multi-label Text Classification Toolkit☆77Updated 5 years ago
- PyTorch implementation of Attention-over-Attention Neural Networks for Reading Comprehension☆61Updated 7 years ago
- ☆97Updated 5 years ago
- CapsNet for NLP☆68Updated 5 years ago
- RAdam optimizer for keras☆71Updated 4 years ago
- ☆39Updated 7 years ago
- Keras implementation of “Gated Linear Unit ”☆23Updated 4 months ago
- Inference with state-of-the-art models (pre-trained by LD-Net / AutoNER / VanillaNER / ...)☆116Updated 5 years ago
- Bidirectional Attention Flow for Machine Comprehension implemented in Keras 2☆64Updated last year
- ☆41Updated this week