Aligning pretrained language models with instruction data generated by themselves.

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Borrow openNMT codes to implememt DRS parser for various languages

Pre-trained word vectors of 30+ languages

Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.

The codes to the paper "Discourse Representation Structure Parsing"

NCRF++, a Neural Sequence Labeling Toolkit. Easy use to any sequence labeling tasks (e.g. NER, POS, Segmentation). It includes character LSTM/CNN, word LSTM/CNN and softmax/CRF components.

EACL 2017

reproduce "Attention Modeling for Targeted Sentiment"

IWPT

TACL 2017

YEDDA: A Lightweight Collaborative Text Span Annotation Tool. Code for ACL 2018 Best Demo Paper Nomination.