【 Albert 】
ALBERT: A LITE BERT FOR SELF-SUPERVISED LEARNING OF LANGUAGE REPRESENTATIONS
论文链接:https://arxiv.org/pdf/1909.11942.pdf
GitHub:https://github.com/brightmart/albert_zh
【 SpanBERT 】
SpanBERT: Improving Pre-training by Representing and Predicting Spans
论文链接:https://arxiv.org/pdf/1907.10529.pdf
GitHub:https://github.com/facebookresearch/SpanBERT
【 RoBERTa 】
论文链接:https://arxiv.org/pdf/1907.11692.pdf
GitHub: https://github.com/brightmart/roberta_zh
【 ERNIE 2.0 】
Ernie 2.0: A continual pre-training framework for language understanding
论文链接:https://arxiv.org/pdf/1907.12412.pdf?source=post_page
GitHub:https://github.com/PaddlePaddle/ERNIE
【 ERNIE 1.0 】
ERNIE: Enhanced Representation through Knowledge Integration
论文链接: https://arxiv.org/pdf/1904.09223.pdf
GitHub:https://github.com/PaddlePaddle/ERNIE
【 OpenAI GPT2 】
Radford, A., et al. (2019). "Language models are unsupervised multitask learners." OpenAI Blog 1(8).
{ GitHub: https://github.com/openai/gpt-2 }
【 XLNet 】
{ GitHub: https://github.com/zihangdai/xlnet }
{ Chinese-pretrained-model GitHub: https://github.com/ymcui/Chinese-PreTrained-XLNet }
【 BERT wwm - ext 】
{ GitHub: https://github.com/ymcui/Chinese-BERT-wwm }
【 BERT wwm 】
哈工大讯飞联合发布全词覆盖中文BERT预训练模型
{ GitHub: https://github.com/ymcui/Chinese-BERT-wwm }
【 BERT 】
{ GitHub: BERT }
【 ELMo 】
Peters, M. E., et al. (2018). "Deep contextualized word representations." arXiv preprint arXiv:1802.05365. NAACL2018最佳论文
【 OpenAI GPT 】
【 word2vec (Skip-gram model)】
【 Attention 】
中文词向量:
腾讯800W中文词 song yan老师出品 https://ai.tencent.com/ailab/nlp/embedding.html