5 datasets found

Tags: story understanding

Filter Results

  • ROCStories corpus

    The ROCStories corpus contains 98,162 five-sentence stories for evaluating story understanding and script learning.

  • ROCStories

    The ROCStories corpus is a collection of crowdsourced five-sentence everyday stories rich in causal and temporal relations.

  • SyMoN

    The SyMoN dataset is a benchmark for video-text alignment.

  • GLUCOSE

    GLUCOSE is a large-scale dataset of implicit commonsense knowledge, encoded as causal mini-theories about the world, each grounded in a narrative context.

  • COPES

    The COPES dataset is a benchmark for event causality extraction. It contains 340 stories and 1360 event pairs.
You can also access this registry using the API (see API Docs).