acknowledge.md

Acknowledgement

• Vanilla Glyce is developed based on the previous SOTA model. Therefore, we would like to thank those who release their code.

  • Chinese NER Using Lattice LSTM
  • Subword Encoding in Lattice LSTM for Chinese Word Segmentation
  • Character-based Joint Segmentation and POS Tagging for Chinese using Bidirectional RNN-CRF
  • Bag-of-Words as Target for Neural Machine Translation
  • Syntax for Semantic Role Labeling, To Be, Or Not To Be
  • Bilateral Multi-Perspective Matching for Natural Language Sentences

• Glyce-BERT is developed based on PyTorch implementation by HuggingFace. And pretrained BERT model is released by Google's pre-trained models.

  • BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
  • Pretrained PyTorch models for Google's BERT Released by HuggingFace