QuALITY: Question Answering with Long Input Texts, Yes!

Autor:	Pang, Richard Yuanzhe, Parrish, Alicia, Joshi, Nitish, Nangia, Nikita, Phang, Jason, Chen, Angelica, Padmakumar, Vishakh, Ma, Johnny, Thompson, Jana, He, He, Bowman, Samuel R.
Rok vydání:	2021
Předmět:	Computer Science - Computation and Language
Druh dokumentu:	Working Paper
Popis:	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%). Comment: NAACL 2022
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2112.08608 Zobrazit plný text záznamu View this record from Arxiv