Great Service! Fine-grained Parsing of Implicit Arguments
This work addresses the challenge of understanding implicit and underspecified language in NLP, which is important for applications like web review analysis, though it appears incremental as it builds on existing datasets and methods.
The researchers tackled the problem of parsing implicit arguments in natural language processing by developing the first transition-based neural parser for this task and testing it on an improved dataset of fine-grained implicit arguments. They found that certain types of implicit arguments are more difficult to parse than others, with a simpler system achieving higher accuracy in recovering implicit arguments despite lower overall parsing scores.
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.