Edy-Barraza / Transformer_Distillation
Knowledge Distillation For Transformer Language Models
☆52Updated last year
Alternatives and similar repositories for Transformer_Distillation:
Users that are interested in Transformer_Distillation are comparing it to the libraries listed below
- Distilling BERT using natural language generation.☆36Updated last year
- ☆47Updated 4 years ago
- MAsked Sequence to Sequence (MASS) pre-training for language generation☆21Updated 6 years ago
- modification of official bert for downstream task☆31Updated 2 years ago
- ☆59Updated 5 years ago
- Record papers for some NLP related area☆24Updated 3 years ago
- This is the code for "Learning Sentiment Memories for Sentiment Modification without Parallel Data".☆54Updated 6 years ago
- ☆83Updated 5 years ago
- An Implementation of Bidirectional Attention Flow☆40Updated 7 years ago
- An "end-to-end trainable task-oriented dialogue model" implementation.☆37Updated 2 years ago
- Tensorflow implementation of Bi-directional RNN Langauge Model☆38Updated 6 years ago
- ☆46Updated 7 months ago
- PyTorch port of BERT ML model☆16Updated 6 years ago
- code for Question Condensing Networks for Answer Selection in Community Question Answering☆14Updated 6 years ago
- Deep Unknown Intent Detection with Margin Loss (ACL2019)☆34Updated 2 years ago
- PyTorch implementation of Attention-over-Attention Neural Networks for Reading Comprehension☆60Updated 7 years ago
- A large-scale cleaned Chinese chitchat corpus and Chinese dialogpt models☆34Updated 4 years ago
- BERT Extension in TensorFlow☆30Updated 5 years ago
- NAACL'19: "Jointly Optimizing Diversity and Relevance in Neural Response Generation"☆74Updated 4 years ago
- Multitask Learning for Machine Reading Comprehension, NAACL 2019☆100Updated 4 years ago
- Knowledge Distillation from BERT☆52Updated 6 years ago
- dstc7-noesis☆46Updated 5 years ago
- ☆17Updated 2 years ago
- This repo is code for the COLING 2018 paper: Sequence-to-sequence Data Augmentation for Dialogue Language Understanding.☆76Updated 3 years ago
- Ordered Neurons LSTM☆30Updated 3 years ago
- The code for "An Auto-Encoder Matching Model for Learning Utterance-Level Semantic Dependency in Dialogue Generation" （EMNLP 2018)☆47Updated 6 years ago
- Codes for our paper at EMNLP2019☆36Updated 5 years ago
- ☆24Updated 5 years ago
- EMNLP'19: Bridging the Gap between Relevance Matching and Semantic Matching for Short Text Similarity Modeling☆77Updated 2 years ago
- ☆50Updated last year