Great Service! Fine-grained Parsing of Implicit Arguments

TL;DR

This paper introduces a new neural parser capable of handling implicit arguments in meaning representations, improving understanding of underspecified language in NLP.

Contribution

It presents the first transition-based neural parser for implicit arguments and re-annotates an existing dataset for better evaluation.

Findings

Certain implicit argument types are more difficult to parse.

Simpler transition system yields higher accuracy for implicit arguments.

Current NLP models have limitations in reasoning about implicit content.

Abstract

Broad-coverage meaning representations in NLP mostly focus on explicitly expressed content. More importantly, the scarcity of datasets annotating diverse implicit roles limits empirical studies into their linguistic nuances. For example, in the web review "Great service!", the provider and consumer are implicit arguments of different types. We examine an annotated corpus of fine-grained implicit arguments (Cui and Hershcovich, 2020) by carefully re-annotating it, resolving several inconsistencies. Subsequently, we present the first transition-based neural parser that can handle implicit arguments dynamically, and experiment with two different transition systems on the improved dataset. We find that certain types of implicit arguments are more difficult to parse than others and that the simpler system is more accurate in recovering implicit arguments, despite having a lower overall parsing score, attesting current reasoning limitations of NLP models. This work will facilitate a better understanding of implicit and underspecified language, by incorporating it holistically into meaning representations.