Revisiting Shallow Discourse Parsing in the PDTB-3: Handling Intra-sentential Implicits

TL;DR

This paper analyzes the challenges of identifying and classifying intra-sentential implicit discourse relations in PDTB-3, emphasizing the need for models to locate arguments and determine their sense within sentences.

Contribution

It introduces a detailed analysis of discourse parsing for intra-sentential implicits, highlighting the complexities and proposing directions for improving model performance.

Findings

Model performance varies with different scenarios

Limitations identified in current parsing approaches

Future directions suggested for better intra-sentential implicit detection

Abstract

In the PDTB-3, several thousand implicit discourse relations were newly annotated \textit{within} individual sentences, adding to the over 15,000 implicit relations annotated \textit{across} adjacent sentences in the PDTB-2. Given that the position of the arguments to these \textit{intra-sentential implicits} is no longer as well-defined as with \textit{inter-sentential implicits}, a discourse parser must identify both their location and their sense. That is the focus of the current work. The paper provides a comprehensive analysis of our results, showcasing model performance under different scenarios, pointing out limitations and noting future directions.