liucongg / GPT2-NewsTitle
Chinese NewsTitle Generation Project by GPT2.带有超级详细注释的中文GPT2新闻标题生成项目。
☆1,103Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for GPT2-NewsTitle
- 中文生成式预训练模型☆555Updated 2 years ago
- 一键中文数据增强包 ; NLP数据增强、bert数据增强、EDA:pip install nlpcda☆1,773Updated 6 months ago
- An implement of the paper of EDA for Chinese corpus.中文语料的EDA数据增强工具。NLP数据增强。论文阅读笔记。☆1,356Updated 2 years ago
- pytorch实现 Bert 做seq2seq任务,使用unilm方案,现在也可以做自动摘要,文本分类,情感分析,NER,词性标注等任务,支持t5模型,支持GPT2进行文章续写。☆1,287Updated 2 years ago
- 基于Pytorch的,中文语义相似度匹配模型(ABCNN、Albert、Bert、BIMPM、DecomposableAttention、DistilBert、ESIM、RE2、Roberta、SiaGRU、XlNet)☆787Updated 4 years ago
- 基于GPT2的中文摘要生成模型☆413Updated last year
- CLUENER2020 中文细粒度命名实体识别 Fine Grained Named Entity Recognition☆1,445Updated last year
- 记录本人整理的一些数据集☆1,003Updated 2 years ago
- 命名实体识别实践与探索☆706Updated 2 years ago
- 天池中药说明书实体识别挑战冠军方案;中文命名实体识别;NER; BERT-CRF & BERT-SPAN & BERT-MRC;Pytorch☆921Updated 3 years ago
- Revisiting Pre-trained Models for Chinese Natural Language Processing (MacBERT)☆645Updated last year
- Pre-trained Chinese ELECTRA(中文ELECTRA预训练模型)☆1,402Updated last year
- Open Language Pre-trained Model Zoo☆987Updated 2 years ago
- 机器阅读理解 冠军/亚军代码及中文预训练MRC模型☆732Updated last year
- RoBERTa中文预训练模型: RoBERTa for Chinese☆2,614Updated 3 months ago
- 基于Pytorch的Bert应用,包括命名实体识别、情感分析、文本分类以及文本相似度等☆701Updated 3 years ago
- 提供一款中文版生成式摘要服务☆322Updated this week
- a bert for retrieval and generation☆844Updated 3 years ago
- Chinese NER(Named Entity Recognition) using BERT(Softmax, CRF, Span)☆2,085Updated last year
- Pre-Trained Chinese XLNet(中文XLNet预训练模型)☆1,653Updated last year
- DeepIE: Deep Learning for Information Extraction☆1,940Updated last year
- ☆402Updated 8 months ago
- code for ACL 2020 paper: FLAT: Chinese NER Using Flat-Lattice Transformer☆1,001Updated 2 years ago
- 高质量中文预训练模型集合:最先进大模型、最快小模型、相似度专门模型☆803Updated 4 years ago
- Computing similarity of two sentences with google's BERT algorithm。利用Bert计算句子相似度。语义相似度计算。文本相似度计算。☆495Updated last year
- 端到端的长本文摘要模型(法研杯2020司法摘要赛道)☆387Updated 5 months ago
- Code for ACL 2021 paper "ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information"☆541Updated last year
- Large-scale Pre-training Corpus for Chinese 100G 中文预训练语料☆922Updated 2 years ago
- 一行代码使用BERT生成句向量,BERT做文本分类、文本相似度计算☆1,652Updated 5 years ago
- An off-the-shelf tool for Chinese Keyphrase Extraction 一个快速从中文里抽取关键短语的工具,仅占35M内存 www.jionlp.com☆538Updated 11 months ago