kbqa

自然语言处理、知识图谱、对话系统三大技术研究与应用。

北京航空航天大学大数据高精尖中心自然语言处理研究团队开展了智能问答的研究与应用总结。包括基于知识图谱的问答（KBQA），基于文本的问答系统（TextQA），基于表格的问答系统（TableQA）、基于视觉的问答系统（VisualQA）和机器阅读理解（MRC）等，每类任务分别对学术界和工业界进行了相关总结。

中文知识库问答代码，CCKS2019 CKBQA评测第四名解决方案

A collection of some materials of knowledge graph question answering

KgCLUE: 大规模中文开源知识图谱问答

🤖 Neural SPARQL Machines for Knowledge Graph Question Answering.

NLP research：基于tensorflow的nlp深度学习项目，支持文本分类/句子匹配/序列标注/文本生成 四大任务

Code & data accompanying the NAACL 2019 paper "Bidirectional Attentive Memory Networks for Question Answering over Knowledge Bases"

Question answering over Freebase (single-relation)

医药知识图谱自动问答系统实现，包括构建知识图谱、基于知识图谱的流水线问答以及前端实现。实体识别（基于词典+BERT_CRF）、实体链接（Sentence-BERT做匹配）、意图识别（基于提问词+领域词词典）。

Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals. WSDM 2021.

Pytorch implementation of baseline models of KQA Pro, a large-scale dataset of complex question answering over knowledge base.

SPARQA: Skeleton-based Semantic Parsing for Complex Questions over Knowledge Bases (AAAI 2020)

You can find the most recent KGQA benchmark numbers from publications here.

Source code and data for our long paper (Wu et al., 2019)

知识图谱初探，关系抽取，实体抽取，基于kb的问答，基于es的问答，知识图谱可视化

COVID-2019 中文知识问答系统

以Spring Boot框架为载体，通过集成hanLP、neo4j、spark-mllib实现基于电影知识图谱的简易问答系统。

Code & data accompanying the WSDM 2021 paper "Personalized Food Recommendation as Constrained Question Answering over a Large-scale Food Knowledge Graph"

kbqa task-oriented qa seq2seq ir neo4j jena seq2seq tf chatbot chat