@InProceedings{boratko-EtAl:2018:W18-26,
  author    = {Boratko, Michael  and  Padigela, Harshit  and  Mikkilineni, Divyendra  and  Yuvraj, Pritish  and  Das, Rajarshi  and  McCallum, Andrew  and  Chang, Maria  and  Fokoue-Nkoutche, Achille  and  Kapanipathi, Pavan  and  Mattei, Nicholas  and  Musa, Ryan  and  Talamadupula, Kartik  and  Witbrock, Michael},
  title     = {A Systematic Classification of Knowledge, Reasoning, and Context within the ARC Dataset},
  booktitle = {Proceedings of the Workshop on Machine Reading for Question Answering},
  month     = {July},
  year      = {2018},
  address   = {Melbourne, Australia},
  publisher = {Association for Computational Linguistics},
  pages     = {60--70},
  abstract  = {The recent work of Clark et al. (2018) introduces the AI2 Reasoning Challenge (ARC) and the associated ARC dataset that partitions open domain, complex science questions into easy and challenge sets. That paper includes an analysis of 100 questions with respect to the types of knowledge and reasoning required to answer them; however, it does not include clear definitions of these types, nor does it offer information about the quality of the labels. We propose a comprehensive set of definitions of knowledge and reasoning types necessary for answering the questions in the ARC dataset. Using ten annotators and a sophisticated annotation interface, we analyze the distribution of labels across the challenge set and statistics related to them. Additionally, we demonstrate that although naive information retrieval methods return sentences that are irrelevant to answering the query, sufficient supporting text is often present in the (ARC) corpus. Evaluating with human-selected relevant sentences improves the performance of a neural machine comprehension model by 42 points.},
  url       = {http://www.aclweb.org/anthology/W18-2607}
}