xianghuisun / Chinese_KGQA
该仓库目的是实现基于知识图谱的中文问答系统
☆51Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for Chinese_KGQA
- CCKS2020 面向中文短文本的实体链指任务。主要思路为:使用基于BiLSTM和Attention的语义模型进行Query和Doc的文本匹配,再针对匹配度进行pairwise排序,从而选出最优的知识库实体。☆46Updated 3 years ago
- 基于“Seq2Seq+前缀树”的知识图谱问答☆71Updated 2 years ago
- 端到端的基于知识图谱的问答系统,分为实体识别和关系分类两部,在BERT基础上做多任务联合训练。☆30Updated 5 years ago
- Knowledge Graph☆169Updated 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☆99Updated 3 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☆50Updated 3 years ago
- 使用多头的思想来进行命名实体识别☆33Updated 3 years ago
- ccks2020基于本体的金融知识图谱自动化构建技术评测第五名方法总结☆48Updated 2 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 2 years ago
- TPlinker for NER 中文/英文命名实体识别☆122Updated 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】☆25Updated last year
- 基于bert_mrc的中文命名实体识别☆43Updated 2 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【知识图谱篇】☆18Updated 2 years ago
- implementation SlotGated SLU model for keras☆34Updated 3 years ago
- 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 4 years ago
- GPLinker_pytorch☆77Updated 2 years ago
- PRGC: Potential Relation and Global Correspondence Based Joint Relational Triple Extraction☆111Updated 3 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 3 years ago
- ☆17Updated 2 years ago
- Chinese Knowledge Base Question Answering, 中文知识问答☆23Updated 4 years ago
- lic2020关系抽取比赛,使用Pytorch实现苏神的模型。☆102Updated 4 years ago
- 基于bert的中文实体链接☆29Updated 3 years ago
- benchmark of KgCLUE, with different models and methods☆26Updated 2 years ago
- CHIP2021-Task3-临床术语标准化任务-开源代码☆42Updated 2 years ago
- 基于pytorch的GlobalPointer进行中文命名实体识别。☆36Updated last year
- [Unofficial] Predict code for AAAI 2022 paper: Unified Named Entity Recognition as Word-Word Relation Classification☆50Updated 2 years ago
- pytorch Efficient GlobalPointer☆51Updated 2 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)☆42Updated 2 years ago
- A system for CCKS2019-CKBQA, whose single system reach 0.69 and ensemble system reach 0.73☆41Updated 3 years ago