Extending Implicit Discourse Relation Recognition to the PDTB-3

TL;DR

This paper explores the expanded PDTB-3 dataset for implicit discourse relation recognition, showing that the new annotations affect the difficulty of identifying relation locations and senses, and proposes baseline methods for future research.

Contribution

It introduces methods tailored to the PDTB-3's new annotations, providing a foundation for improved implicit discourse relation recognition.

Findings

Implicit relation sense identification is simplified by new annotations.

Locating implicit relations remains challenging due to complex annotations.

Baseline methods offer a starting point for future improvements.

Abstract

The PDTB-3 contains many more Implicit discourse relations than the previous PDTB-2. This is in part because implicit relations have now been annotated within sentences as well as between them. In addition, some now co-occur with explicit discourse relations, instead of standing on their own. Here we show that while this can complicate the problem of identifying the location of implicit discourse relations, it can in turn simplify the problem of identifying their senses. We present data to support this claim, as well as methods that can serve as a non-trivial baseline for future state-of-the-art recognizers for implicit discourse relations.