nem6ishi / wat17Links
This is the official code used for WAT 2017 Description Paper titled A Bag of Useful Tricks for Practical Neural Machine Translation: Embedding Layer Initialization and Large Batch Size.
☆12Updated 7 years ago
Alternatives and similar repositories for wat17
Users that are interested in wat17 are comparing it to the libraries listed below
Sorting:
- Notes on Deep Reinforcement Learning for Natural Language Processing papers☆30Updated 7 years ago
- Context Aware Language Models☆28Updated 6 years ago
- Code for EMNLP 2016 paper: Morphological Priors for Probabilistic Word Embeddings☆53Updated 8 years ago
- Uncovering divergent linguistic information in word embeddings with lessons for intrinsic and extrinsic evaluation☆63Updated 6 years ago
- Code for the paper "Extreme Adaptation for Personalized Neural Machine Translation"☆42Updated 3 years ago
- Converts Quora's new NLU dataset to SNLI txt/jsonl format, plus test/dev split, tokenization.☆14Updated 8 years ago
- 2019 NAACL NLI with Deep Learning tutorial site.☆31Updated 5 years ago
- Utility scripts in Python☆37Updated last week
- ☆29Updated 7 years ago
- Variants of Multi-Perspective Convolutional Neural Networks☆22Updated last year
- Source code and data for the paper "Towards String-to-Tree Neural Machine Translation"☆16Updated 7 years ago
- Neural Machine Translation (attention and zero-shot)☆6Updated 8 years ago
- Slides/code for the Lisbon machine learning school 2017☆28Updated 7 years ago
- Code for upcoming TACL paper w/ Graham Neubig, "Neural Lattice Language Models".☆48Updated 7 years ago
- Interactive tutorial on the Forward-Backward Expectation Maximization algorithm☆30Updated 9 years ago
- Auto-Encoding Variational Neural Machine Translation☆16Updated 5 years ago
- ☆33Updated 6 years ago
- ☆19Updated 8 years ago
- Variational Auto-Encoder for Dialogue Generation Models & Experiments☆35Updated 7 years ago
- ☆37Updated 6 years ago
- structured attention encoder☆13Updated 7 years ago
- Document context language models☆22Updated 9 years ago
- A simple Python wrapper for the ClearNLP constituents-to-dependencies converter☆10Updated 9 years ago
- AskUbuntu Question Dataset☆69Updated 8 years ago
- ☆47Updated 8 years ago
- Word embedding approach based on a dynamic log-linear model☆54Updated 7 years ago
- ☆44Updated 7 years ago
- Pre-training character n-gram embeddings☆22Updated last year
- Code for ICLR 2019 paper 'CBOW Is Not All You Need: Combining CBOW with the Compositional Matrix Space Model'☆21Updated 6 years ago
- Recurrent versus Recursive Approaches Towards Compositionality in Semantic Vector Spaces.☆13Updated 3 years ago