Implicit arguments, which cannot be detected solely through syntactic cues, make it harder to extract predicate-argument tuples. We present a new model for implicit argument prediction that draws on reading comprehension, casting the predicate-argument tuple with the missing argument as a query. We also draw on pointer networks and multi-hop computation. Our model shows good performance on an argument cloze task as well as on a nominal implicit argument prediction task.
@article{arxiv.1811.03554,
title = {Implicit Argument Prediction as Reading Comprehension},
author = {Pengxiang Cheng and Katrin Erk},
journal= {arXiv preprint arXiv:1811.03554},
year = {2018}
}