wzzzd / pretrain_bert_with_maskLM
使用Mask LM预训练任务来预训练Bert模型。训练垂直领域语料的模型表征,提升下游任务的表现。
☆43Updated 2 years ago
Alternatives and similar repositories for pretrain_bert_with_maskLM:
Users that are interested in pretrain_bert_with_maskLM are comparing it to the libraries listed below
- 复现论文《Simplify the Usage of Lexicon in Chinese NER》☆42Updated 3 years ago
- GPLinker_pytorch☆81Updated 2 years ago
- GlobalPointer的优化版/NER实体识别☆116Updated 3 years ago
- NLP关系抽取:序列标注、层叠式指针网络、Multi-head Selection、Deep Biaffine Attention☆100Updated 3 years ago
- Tplinker注释,中文数据集适配版本☆59Updated 4 years ago
- TPlinker for NER 中文/英文命名实体识别☆123Updated 3 years ago
- 基于bert_mrc的中文命名实体识别☆44Updated 2 years ago
- NER任务SOTA模型BERT_MRC☆60Updated last year
- 基于pytorch的百度UIE命名实体识别。☆57Updated 2 years ago
- 苏神SPACE pytorch版本复现☆42Updated 3 years ago
- 句子匹配模型,包括无监督的SimCSE、ESimCSE、PromptBERT,和有监督的SBERT、CoSENT。☆98Updated 2 years ago
- A simple framework for building some basic NLP tasks☆59Updated 2 years ago
- 中文数据集下SimCSE+ESimCSE的实现☆191Updated 2 years ago
- CMeEE/CBLUE/NER实体识别☆127Updated 2 years ago
- GAIIC2022商品标题实体识别Baseline,使用GlobalPointer实现,线上0.80349☆53Updated 2 years ago
- 论文复现《Named Entity Recognition as Dependency Parsing》☆129Updated 3 years ago
- pytorch Efficient GlobalPointer☆53Updated 2 years ago
- Knowledge Graph☆171Updated 2 years ago
- https://tianchi.aliyun.com/dataset/dataDetail?dataId=95414☆30Updated 3 years ago
- NLP句子编码、句子embedding、语义相似度:BERT_avg、BERT_whitening、SBERT、SmiCSE☆176Updated 3 years ago
- ☆88Updated 3 years ago
- 基于词汇信息融合的中文NER模型☆165Updated 3 years ago
- lic2020关系抽取比赛,使用Pytorch实现苏神的模型。☆101Updated 4 years ago
- 百度2021年语言与智能技术竞赛多形态信息抽取赛道关系抽取部分torch版baseline☆52Updated 3 years ago
- 该仓库主要记录 NLP 算法工程师相关的顶会论文研读笔记【信息抽取篇】☆26Updated 2 years ago
- A solution to 2021-CCKS-QA-Task(https://tianchi.aliyun.com/competition/entrance/531904/introduction)☆49Updated 2 years ago
- ☆278Updated 2 years ago
- 多标签文本分类☆30Updated 3 years ago
- 中文无监督SimCSE Pytorch实现☆134Updated 3 years ago
- code for ACL2020:《FLAT: Chinese NER Using Flat-Lattice Transformer》 我注释&修改&添加了部分源码,使得大家更容易复现这个代码。☆56Updated 4 years ago