Implicit Argument Prediction as Reading Comprehension

TL;DR

This paper introduces a novel reading comprehension-based model for implicit argument prediction, leveraging pointer networks and multi-hop reasoning to improve extraction of predicate-argument tuples with missing arguments.

Contribution

It proposes a new approach that treats implicit argument prediction as a reading comprehension problem, incorporating advanced neural techniques for better accuracy.

Findings

Good performance on argument cloze task

Effective in nominal implicit argument prediction

Demonstrates the viability of reading comprehension methods for argument prediction

Abstract

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.