thorjohnsen / bert
TensorFlow code and pre-trained models for BERT
☆17Updated 6 years ago
Alternatives and similar repositories for bert:
Users that are interested in bert are comparing it to the libraries listed below
- NLU: domain-intent-slot; text2SQL☆75Updated 4 years ago
- ☆59Updated 5 years ago
- ☆17Updated 6 years ago
- datasets of natural language understanding and dialogue state tracking☆144Updated 4 years ago
- An "end-to-end trainable task-oriented dialogue model" implementation.☆37Updated 2 years ago
- Conversational Word Embedding for Retrieval-based Dialog System (ACL2020)☆30Updated 4 years ago
- CIKM 2019: Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots☆84Updated 5 years ago
- Task-oriented dialog system toolkits☆85Updated 2 years ago
- Baseline for the CNLI corpus☆56Updated 5 years ago
- Webpage for the DSTC8 - NOESIS II: Predicting Responses☆48Updated 2 years ago
- Re-rank n-best lists using additional features.☆28Updated 6 years ago
- add BERT to encoder part for https://github.com/memray/seq2seq-keyphrase-pytorch☆79Updated 6 years ago
- ☆50Updated 6 years ago
- Tensorflow implementation for MRFN in Retrieval-based Chatbots☆49Updated 5 years ago
- Fully Statistical Neural Belief Tracker (Mrkšić and Vulić, ACL 2018)☆168Updated last year
- Chinese Version of ACL 2020 PC Blogs (ACL 2020程序委员会博文中文版)☆14Updated 4 years ago
- ☆47Updated 4 years ago
- [ACL 2020] DeFormer: Decomposing Pre-trained Transformers for Faster Question Answering☆120Updated last year
- Source code for our EMNLP19 paper "Retrieval-guided Dialogue Response Generation via a Matching-to-Generation Framework"☆37Updated 5 years ago
- Resources of our paper at AAAI-19 ``Response Generation by Context-aware Prototype Editing"☆78Updated 5 years ago
- this is roberta wwm base distilled model which was distilled from roberta wwm by roberta wwm large☆65Updated 5 years ago
- A parser of the Multi-Domain Wizard-of-Oz dataset (MultiWOZ)☆67Updated 6 years ago
- ☆62Updated 5 years ago
- Code for the paper: GCDT: A Global Context Enhanced Deep Transition Architecture for Sequence Labeling☆67Updated 5 years ago
- ☆121Updated 2 years ago
- multi-gpu pre-training in one machine for BERT without horovod (Data Parallelism)☆172Updated 2 weeks ago
- BERT-DST: Scalable End-to-End Dialogue State Tracking with Bidirectional Encoder Representations from Transformer☆101Updated 4 years ago
- Code for Synchronous Bidirectional Neural Machine Translation (SB-NMT)☆66Updated 5 years ago
- For the new students who just join a NLP group☆27Updated 7 years ago
- a simple yet complete implementation of the popular BERT model☆127Updated 5 years ago