@misc{kasai2021billboard,
    title   = {Bidimensional Leaderboards: Generate and Evaluate Language Hand in Hand},
    author  = {Jungo Kasai and Keisuke Sakaguchi and Ronan Le Bras and Lavinia Dunagan and Jacob Morrison and Alexander R. Fabbri and Yejin Choi and Noah A. Smith},
    year    = {2021},
    url     = {https://arxiv.org/abs/2112.04139}, 
}

@misc{kasai2021thumb,
    title   = {Transparent Human Evaluation for Image Captioning},
    author  = {Jungo Kasai and Keisuke Sakaguchi and Lavinia Dunagan and Jacob Morrison and Ronan Le Bras and Yejin Choi and Noah A. Smith},
    year    = {2021},
    url     = {https://arxiv.org/abs/2111.08940}, 
}

@article{fabbri2021summeval,
    title   = {{SummEval}: Re-evaluating Summarization Evaluation},
    author  = {Fabbri, Alexander R and Kry{\'s}ci{\'n}ski, Wojciech and McCann, Bryan and Xiong, Caiming and Socher, Richard and Radev, Dragomir},
    journal = {TACL},
    year    = {2021},
    url     = {https://arxiv.org/abs/2007.12626},
}

@misc{freitag2021experts,
      title={Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translation}, 
      author={Markus Freitag and George Foster and David Grangier and Viresh Ratnakar and Qijun Tan and Wolfgang Macherey},
      year={2021},
      url={https://arxiv.org/abs/2104.14478},
}