Multi-Label Classification for Implicit Discourse Relation Recognition

TL;DR

This paper explores multi-label classification frameworks for implicit discourse relation recognition, addressing the limitations of prior single-label approaches and analyzing their effectiveness on the PDTB dataset.

Contribution

It introduces multi-label classification methods for discourse relation recognition, demonstrating their effectiveness and providing comprehensive analysis and insights.

Findings

Multi-label methods do not reduce performance on single-label cases.

The study offers detailed analysis of multi-label classification in discourse relation recognition.

Provides a foundation for future research in discourse relation modeling.

Abstract

Discourse relations play a pivotal role in establishing coherence within textual content, uniting sentences and clauses into a cohesive narrative. The Penn Discourse Treebank (PDTB) stands as one of the most extensively utilized datasets in this domain. In PDTB-3, the annotators can assign multiple labels to an example, when they believe that multiple relations are present. Prior research in discourse relation recognition has treated these instances as separate examples during training, and only one example needs to have its label predicted correctly for the instance to be judged as correct. However, this approach is inadequate, as it fails to account for the interdependence of labels in real-world contexts and to distinguish between cases where only one sense relation holds and cases where multiple relations hold simultaneously. In our work, we address this challenge by exploring various multi-label classification frameworks to handle implicit discourse relation recognition. We show that multi-label classification methods don't depress performance for single-label prediction. Additionally, we give comprehensive analysis of results and data. Our work contributes to advancing the understanding and application of discourse relations and provide a foundation for the future study