20190121 | 清华大学AI研究院知识智能研究中心发布会的记录

Minute and thoughts of the launch conference of THUKC (清华大学人工智能研究院知识智能研究中心).
Mainly about the part of Commonsense-Awared Natural Language Generation (常识知识感知的语言生成, 黄民烈)

Commonsense Extraction

  • what is Commonsense Knowledge (CS Know.)
  • what is the Boundary of commonsense
  • Commonsense Extraction
    • From Embedding
      • Extracting Commonsense Properties from Embeddings with Limited Human Guidance. 2018
    • Commonsense Knowledge base completion
      • Commonsense Knowledge base Completion. 2018
    • From RAW data(text, image)
      • Automatic Extraction of Commonsense LocatedNear Knowledge. 2018

Commonsense Knowledge in RC

  • 代表工作:Knowledgeable Reader

Commonsense Knowledge to Intent, Reaction, Emotion, etc

  • 代表工作:
    • Event2Mind: Commonsense Inference on Events, Intents and Reaction
    • Modeling Naive Psychology of Characters in Simple Commonsense Stories
  • AI2 实验室做了大量这方面的工作,相关调研:link

Commonsense to Controllable TG

  • 黄民烈老师组的一些很好的工作(黄老师称这些工作是常识知识感知的语言生成的初步探索):
    • Commonsense Knowledge Aware Conversation Generation with Graph Attention. IJCAI,2018.(distinguished paper)[1]
    • Story Ending Generation with Incremental Encoding Commonsense Knowledge. AAAI,2019.
    • 学习笔记:note_link
  • Three Fundamental problems in current Neural Language Generation Models
    • semantics(real understanding)
    • Consistency(long text generation)
    • Logic(reasonable and making sense)
    • 在评价方面,关于如何评价生成的文本具有逻辑性还是个挑战(相关研究点:文本生成评价指标(BLEU、ROUGE等)的研究)
  • New Architecture:
    • symbolic knowledge + planning + neural computing

发布的重要资源

知识智能研究中心:http://ai.tsinghua.edu.cn/kirc/#

  • 中英文跨语言百科知识图谱XLORE — 世界知识
    • 特点:
      • 大规模跨语言百科知识图谱
      • 通过融合维基百科和百度百科,并对百科知识进行结构化和跨语言链接构建而成。
      • 以结构化形式描述客观世界中的概念、实例、属性及其丰富语义关系。
      • XLORE目前包含约247万概念、44.6万属性/关系、1628万实例和260万跨语言链接。
    • 项目地址:https://xlore.org/
  • 基于义原的开放语言知识库 OpenHowNet — 语言知识常识知识

  1. 1.https://juejin.im/post/5b6a9e085188251a8d37136d
**** END of This Post. Thank for Your READING ****
If you have any Question, welcome to Email me or leave your comments below.