taishan1994 / pytorch_knowledge_distillation
基于Pytorch的知识蒸馏(中文文本分类)
☆16Updated 2 years ago
Alternatives and similar repositories for pytorch_knowledge_distillation:
Users that are interested in pytorch_knowledge_distillation are comparing it to the libraries listed below
- 基于pytorch的TPLinker_plus进行中文命名实体识别☆18Updated last year
- 基于bert_mrc的中文命名实体识别☆43Updated 2 years ago
- 多标签文本分类☆29Updated 3 years ago
- 嵌套命名实体识别 Nested NER☆19Updated 3 years ago
- 基于PaddleNLP开源的抽取式UIE进行医学命名实体识别(torch实现)☆44Updated 2 years ago
- 基于ERNIE的中文NER☆34Updated 2 years ago
- 基于pytorch的百度UIE命名实体识别。☆57Updated 2 years ago
- 本项目是NLP领域一些任务的基准模型实现,包括文本分类、命名实体识别、实体关系抽取、NL2SQL、CKBQA以及BERT的各种下游任务应用。☆47Updated 4 years ago
- pytorch Efficient GlobalPointer☆53Updated 2 years ago
- 多模型中文cnews新闻文本分类☆54Updated 4 years ago
- bert-flat 简化版 添加了很多注释☆15Updated 3 years ago
- NER任务SOTA模型BERT_MRC☆60Updated 11 months ago
- 使用多头的思想来进行命名实体识别☆33Updated 3 years ago
- 基于BERT-MRC(阅读理解)的命名实体识别模型☆19Updated 2 years ago
- GlobalPointer的优化版/NER实体识别☆116Updated 3 years ago
- using lear to do ner extraction☆29Updated 2 years ago
- 基于pytorch的GlobalPointer进行中文命名实体识别。☆36Updated last year
- 利用 HMM、BiLSTM-CRF 及 ALBERT 模型进行中文命名实体识别☆23Updated 2 years ago
- 使用BERT-BiLSTM+CRF进行ner任务(pytorch_lightning版)☆43Updated 2 years ago
- Summary and comparison of Chinese classification models☆34Updated 2 years ago
- Cascade bert+word vec and one layer FLAT, trained by adversarial FGM and Stochastic Weight Averaging☆23Updated 3 years ago
- ☆14Updated 2 years ago
- 2020 “万创杯”中医药天池大数据竞赛——中药说明书实体识别挑战 复盘☆31Updated 4 years ago
- Pytorch进行长文本分类。这里用到的网络有:FastText、TextCNN、TextRNN、TextRCNN、Transformer☆46Updated 4 years ago
- 使用R-BERT模型对人物关系模型进行分类,效果有显著提升。☆24Updated last year
- [Unofficial] Predict code for AAAI 2022 paper: Unified Named Entity Recognition as Word-Word Relation Classification☆52Updated 2 years ago
- albert-fc for RE(Relation Extraction),中文关系抽取☆18Updated last year
- CMeEE/CBLUE/NER实体识别☆126Updated 2 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
- 采用bert进行事件抽取,[cls]进行事件分类,最后一层向量进行序列标注,两个任务同时训练。☆12Updated 3 years ago