Stars
Code & data accompanying the NAACL 2019 paper "Bidirectional Attentive Memory Networks for Question Answering over Knowledge Bases"
从无到有构建一个电影知识图谱，并基于该KG，开发一个简易的KBQA程序。
Source code and data for our long paper (Wu et al., 2019)
CCKS2019中文命名实体识别任务。从医疗文本中识别疾病和诊断、解剖部位、影像检查、实验室检验、手术和药物6种命名实体。现已实现基于jieba和AC自动机的baseline构建、基于BiLSTM和CRF的序列标住模型构建。bert的部分代码主要源于https://github.com/charles9n/bert-sklearn.git 感谢作者。 模型最终测试集得分0.81，还有较大改进…
CCKS 2019 Task 2: Entity Recognition and Linking
中文知识库问答代码，CCKS2019 CKBQA评测第四名解决方案
🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP
A trial of kbqa based on bert for NLPCC2016/2017 Task 5 (基于BERT的中文知识库问答实践，代码可跑通）
基于知识图谱的问答系统，BERT做命名实体识别和句子相似度，分为online和outline模式
A characteristic-rich dataset for factoid question answering described in the paper "On Generating Characteristic-rich Question Sets for QA Evaluation" - EMNLP'16
WebQuestions QA Benchmarking Dataset