bojone / KgCLUE-bert4kerasLinks
基于“Seq2Seq+前缀树”的知识图谱问答
☆70Updated 4 years ago
Alternatives and similar repositories for KgCLUE-bert4keras
Users that are interested in KgCLUE-bert4keras are comparing it to the libraries listed below
Sorting:
- ccks金融事件主体抽取☆74Updated 5 years ago
- Label Mask for Multi-label Classification☆58Updated 4 years ago
- transformers implement (architecture, task example, serving and more)☆96Updated 3 years ago
- 中文版unilm预训练模型☆83Updated 4 years ago
- Pattern-Exploiting Training在中文上的简单实验☆174Updated 5 years ago
- using lear to do ner extraction☆29Updated 3 years ago
- 中文多跳问答数据集☆82Updated 7 years ago
- 句子匹配模型,包括无监督的SimCSE、ESimCSE、PromptBERT,和有监督的SBERT、CoSENT。☆100Updated 3 years ago
- 中文bigbird预训练模型☆96Updated 3 years ago
- 天池-新冠疫情相似句对判定大赛 Rank8☆52Updated 5 years ago
- ☆88Updated 4 years ago
- 机器检索阅读联合学习,莱斯杯:全国第二届“军事智能机器阅读”挑战赛 rank6 方案☆128Updated 5 years ago
- R-Drop方法在中文任务上的简单实验☆91Updated 3 years ago
- ☆51Updated 4 years ago
- RoFormer升级版☆154Updated 3 years ago
- 适用于常见的NLP任务的模板☆35Updated 2 years ago
- Negative sampling for solving the unlabeled entity problem in NER. ICLR-2021 paper: Empirical Analysis of Unlabeled Entity Problem in Nam…☆134Updated 3 years ago
- CCKS 2020: 基于本体的金融知识图谱自动化构建技术评测☆89Updated 3 years ago
- ☆90Updated 5 years ago
- The implementation our EMNLP 2021 paper "Enhanced Language Representation with Label Knowledge for Span Extraction".☆114Updated 2 years ago
- 中文无监督SimCSE Pytorch实现☆135Updated 4 years ago
- IPRE: a Dataset for Inter-Personal Relationship Extraction☆95Updated 6 years ago
- 本项目是CCKS2020实体链指比赛baseline(pytorch)☆19Updated 5 years ago
- 对话改写介绍文章☆98Updated 2 years ago
- pytorch Efficient GlobalPointer☆56Updated 3 years ago
- lic2020关系抽取比赛,使用Pytorch实现苏神的模型。☆103Updated 5 years ago
- 2020语言与智能技术竞赛:面向推荐的对话任务☆52Updated 4 years ago
- A Chinese KBQA dataset with SPARQL annotations.☆144Updated 6 years ago
- 基于 Tensorflow,仿 Scikit-Learn 设计的深度学习自然语言处理框架。支持 40 余种模型类,涵盖语言模型、文本分类、NER、MRC、知识蒸馏等各个领域☆117Updated 2 years ago
- CLUEWSC2020: WSC Winograd模式挑战中文版,中文指代消解任务☆79Updated 5 years ago