taishan1994 / genius_for_your_data
使用GENIUS文本生成模型训练自己的数据集。
☆8Updated last year
Related projects: ⓘ
- 多轮中文聊天机器人,采用GPT2进行微调,清洗聊天数据110w+,采用语义相似度和文本jaccard相似度过滤回话。☆21Updated 2 years ago
- [Unofficial] Predict code for AAAI 2022 paper: Unified Named Entity Recognition as Word-Word Relation Classification☆50Updated 2 years ago
- benchmark of KgCLUE, with different models and methods☆26Updated 2 years ago
- 基于pytorch的百度UIE命名实体识别。☆52Updated last year
- 基于PaddleNLP开源的抽取式UIE进行医学命名实体识别(torch实现)☆41Updated 2 years ago
- using lear to do ner extraction☆29Updated 2 years ago
- ☆10Updated last year
- 基于simcse的中文句向量生成☆14Updated 2 years ago
- ☆13Updated 2 years ago
- implementation SlotGated SLU model for keras☆32Updated 3 years ago
- ☆31Updated this week
- pytorch Efficient GlobalPointer☆50Updated 2 years ago
- ☆32Updated 3 years ago
- 基于seq2edit (Gector) 的中文文本纠错。☆26Updated last year
- A full-process dialogue system that can be deployed online☆97Updated 2 years ago
- ☆57Updated last year
- ☆100Updated 3 years ago
- 开课吧&后厂理工学院_百度NLP项目2:试题数据集多标签文本分类 Models: FastText TextCNN GCN BERT et al.☆48Updated 4 years ago
- 微调预训练语言模型(BERT、Roberta、XLBert等),用于计算两个文本之间的相似度(通过句子对分类任务转换),适用于中文文本☆89Updated 4 years ago
- ☆10Updated 2 years ago
- 中文bigbird预训练模型☆86Updated 2 years ago
- deep training task☆30Updated last year
- 通用kbqa,训练数据来源于ccks2018和2019,图谱数据爬取于百度百科☆24Updated 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。☆96Updated last year
- bert语言模型校验句子的通顺性☆15Updated 4 years ago
- 新闻标题摘要生成模型,基于T5-PEGASUS。News title summary generation model☆16Updated 2 years ago
- 基于bert4keras进行nlp工作,暂时包含文本分类,实体识别,实体关系抽取☆7Updated 3 years ago
- 多标签文本分类☆27Updated 2 years ago
- bert_avg,bert_whitening,sbert,consert,simcse,esimcse 中文句向量表示☆16Updated 2 years ago
- Bert预训练模型fine-tune计算文本相似度☆95Updated last year