随笔分类 - 自然语言处理NLP
论文阅读：Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphs
摘要：从历史到未来的原因:时间知识图的两阶段推理 Abstract Temporal Knowledge Graphs (TKGs) have been developed and used in many different areas. Reasoning on TKGs that predicts
OpenKE 使用日志
摘要：2021.11.8 下载清华NLP的OpenKE 同时使用PyCharm和Anaconda，以Anaconda来配置环境KG，添加了numpy，pytorch，mingw，libpython库 \begin{equation} \frac{1}{\sqrt 2 + \frac{1}{ \sqrt 2
论文阅读：The Role of “Condition”: A Novel Scientific Knowledge Graph Representation and Construction Model
摘要：“条件”的作用:一种新的科学知识图表示与构建模型 Abstract 条件关系在科学观测、假设和陈述中起着重要作用，但是现有的科学知识图谱（SicKgs）与一般领域的知识图谱（KGs）一样，没有考虑事实有效的条件，仅将事实知识表示为一个平面的概念关系网络，从而丧失了推理和探索的重要上下文。 In th
论文阅读：ExCAR: Event Graph Knowledge Enhanced Explainable Causal Reasoning
摘要：ExCAR: 事件图知识增强的可解释因果推理 Abstract Prior work infers the causation between events mainly based on the knowledge induced from the annotated causal event p
论文阅读：Extracting COVID-19 diagnoses and symptoms from clinical text: A new annotated corpus and neural event extraction framework
摘要：从临床文本中提取COVID-19诊断和症状:一个新的标注语料库和神经事件提取框架 Abstract We introduce a span-based event extraction model that jointly extracts all annotated phenomena, achi
事理图谱概述
摘要：事理图谱概述 人工智能与认知智能 从人工智能的发展阶段来看，人工智能先后经历了从计算智能到感知智能再到认知智能的三个发展阶段。在计算智能时代，以神经网络、遗传算法为代表的学习算法，让机器能够帮助人类存储和快速处理海量数据，使得机器开始像人类一样“能说会算”。感知智能时代，机器能够开始看懂和听懂，
