Linguistically-Informed Self-Attention implemented in TensorFlow

Efficient and clean PyTorch reimplementation of "End-to-end Neural Coreference Resolution" (Lee et al., EMNLP 2017).

[WMT 2022 champion system] Vega-MT model and inference scripts

Transfer knowledge from a large DNN or an ensemble of DNNs into a small DNN

(AAAI'20) The source code for the paper "Joint Parsing and Generation for Abstractive Summarization".