Pinned Repositories
XLM
PyTorch original implementation of Cross-lingual Language Model Pretraining.
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
cnn-dailymail
Code to obtain raw texts of the CNN / Daily Mail dataset (non-anonymized) for summarization (python3)
gector
Official implementation of the paper "GECToR – Grammatical Error Correction: Tag, Not Rewrite" // Accepted for publication on BEA15 Workshop (co-located with ACL 2020) https://arxiv.org/abs/2005.12592
kuzukiri
Japanese Text Segmenter for Python written in Rust
NCRFpp
NCRF++, an Open-source Neural Sequence Labeling Toolkit. It includes character LSTM/CNN, word LSTM/CNN and softmax/CRF components.
pke
Python Keyphrase Extraction module
pythonrouge
Python wrapper for evaluating summarization quality by ROUGE package
summarization
implementation of summarization algorithm by python
XLM
PyTorch original implementation of Cross-lingual Language Model Pretraining.
tagucci's Repositories
tagucci/pythonrouge
Python wrapper for evaluating summarization quality by ROUGE package
tagucci/cnn-dailymail
Code to obtain raw texts of the CNN / Daily Mail dataset (non-anonymized) for summarization (python3)
tagucci/summarization
implementation of summarization algorithm by python
tagucci/gector
Official implementation of the paper "GECToR – Grammatical Error Correction: Tag, Not Rewrite" // Accepted for publication on BEA15 Workshop (co-located with ACL 2020) https://arxiv.org/abs/2005.12592
tagucci/kuzukiri
Japanese Text Segmenter for Python written in Rust
tagucci/NCRFpp
NCRF++, an Open-source Neural Sequence Labeling Toolkit. It includes character LSTM/CNN, word LSTM/CNN and softmax/CRF components.
tagucci/pke
Python Keyphrase Extraction module
tagucci/XLM
PyTorch original implementation of Cross-lingual Language Model Pretraining.