Implicit Argument Prediction as Reading Comprehension
This addresses the challenge of extracting predicate-argument tuples in natural language processing, where implicit arguments hinder accuracy, but it is incremental as it builds on existing reading comprehension and pointer network methods.
The paper tackled the problem of predicting implicit arguments in predicate-argument tuples by casting it as a reading comprehension task, achieving good performance on argument cloze and nominal implicit argument prediction tasks.
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.