More Like this

1. “Yes We Can!”: A Practical Approach to Teaching Reproducibility to Undergraduates

   https://doi.org/10.1162/99608f92.9e002f7b  

   Ball, Richard (July 2023, Harvard Data Science Review)
2. RESPECT 2019: Yes, We Still Need to Talk About Diversity in Computing

   https://doi.org/10.1109/MCSE.2018.2887008  

   Washington, Nicki; Barnes, Tiffany; Payton, Jamie; Dunton, Sarah; Stukes, Felesia; Peterfreund, Alan (January 2019, Computing in Science & Engineering)
3. Yes, polygenic sex determination is a thing!

   https://doi.org/10.1016/j.tig.2024.10.003  

   Kocher, Thomas D; Meisel, Richard P; Gamble, Tony; Behrens, Kristen A; Gammerdinger, William J (December 2024, Trends in Genetics)
4. QuALITY: Question Answering with Long Input Texts, Yes!

   https://doi.org/10.18653/v1/2022.naacl-main.391  

   Pang, Richard Yuanzhe; Parrish, Alicia; Joshi, Nitish; Nangia, Nikita; Phang, Jason; Chen, Angelica; Padmakumar, Vishakh; Ma, Johnny; Thompson, Jana; He, He; et al (January 2022, Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies)
5. QuALITY: Question Answering with Long Input Texts, Yes!

   Bowman, Samuel R.; Chen, Angelica; He, He; Joshi, Nitish; Ma, Johnny; Nangia, Nikita; Padmakumar, Vishakh; Pang, Richard Yuanzhe; Parrish, Alicia; Phang, Jason; et al (May 2022, NAACL 2022)

   To enable building and testing models on long-document comprehension, we introduce QuALITY, a multiple-choice QA dataset with context passages in English that have an average length of about 5,000 tokens, much longer than typical current models can process. Unlike in prior work with passages, our questions are written and validated by contributors who have read the entire passage, rather than relying on summaries or excerpts. In addition, only half of the questions are answerable by annotators working under tight time constraints, indicating that skimming and simple search are not enough to consistently perform well. Our baseline models perform poorly on this task (55.4%) and significantly lag behind human performance (93.5%). 

   more » « less