Event2Mind: Commonsense Inference on Events, Intents, and Reactions

  title={Event2Mind: Commonsense Inference on Events, Intents, and Reactions},
  author={Hannah Rashkin and Maarten Sap and Emily Allaway and Noah A. Smith and Yejin Choi},
  • Hannah Rashkin, Maarten Sap, +2 authors Yejin Choi
  • Published 2018
  • Computer Science
  • ArXiv
  • We investigate a new commonsense inference task: given an event described in a short free-form text ("X drinks coffee in the morning"), a system reasons about the likely intents ("X wants to stay awake") and reactions ("X feels alert") of the event's participants. [...] Key Result In addition, we demonstrate how commonsense inference on people's intents and reactions can help unveil the implicit gender inequality prevalent in modern movie scripts.Expand Abstract

    Paper Mentions

    ATOMIC: An Atlas of Machine Commonsense for If-Then Reasoning
    • 117
    • PDF
    Commonsense Reasoning for Natural Language Understanding: A Survey of Benchmarks, Resources, and Approaches
    • 19
    • Highly Influenced
    • PDF
    Does It Make Sense? And Why? A Pilot Study for Sense Making and Explanation
    • 25
    • PDF
    A Knowledge-Enhanced Pretraining Model for Commonsense Story Generation
    • 17
    • PDF
    SemEval-2020 Task 4: Commonsense Validation and Explanation
    • 11
    • PDF
    On the Evaluation of Common-Sense Reasoning in Natural Language Understanding
    • 16
    • PDF
    A Hybrid Neural Network Model for Commonsense Reasoning
    • 11
    • PDF


    Publications referenced by this paper.
    Efficient Estimation of Word Representations in Vector Space
    • 15,094
    • PDF
    A large annotated corpus for learning natural language inference
    • 1,460
    • PDF
    Accurate Unlexicalized Parsing
    • 3,189
    • PDF
    The Berkeley FrameNet Project
    • 2,574
    • PDF
    Convolutional Neural Networks for Sentence Classification
    • 6,714
    • PDF
    Generating Sentences from a Continuous Space
    • 1,138
    • PDF
    Gradient-based learning applied to document recognition
    • 24,365
    • PDF
    The PASCAL Recognising Textual Entailment Challenge
    • 1,370
    • PDF
    On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
    • 2,762
    • Highly Influential
    • PDF
    The Psychological Meaning of Words: LIWC and Computerized Text Analysis Methods
    • 2,697
    • PDF