Labeling Explicit Discourse Relations using Pre-trained Language Models

TL;DR

This paper demonstrates that fine-tuned pre-trained language models can effectively replace hand-crafted features for labeling explicit discourse relations, achieving state-of-the-art results on PDTB 2.0 without linguistic features.

Contribution

It introduces a novel approach using pre-trained language models to outperform traditional models in explicit discourse relation labeling without linguistic features.

Findings

Pre-trained language models outperform previous models on PDTB 2.0.

Fine-tuning pre-trained models can replace linguistic features.

Achieved state-of-the-art F-score in relation extraction.

Abstract

Labeling explicit discourse relations is one of the most challenging sub-tasks of the shallow discourse parsing where the goal is to identify the discourse connectives and the boundaries of their arguments. The state-of-the-art models achieve slightly above 45% of F-score by using hand-crafted features. The current paper investigates the efficacy of the pre-trained language models in this task. We find that the pre-trained language models, when finetuned, are powerful enough to replace the linguistic features. We evaluate our model on PDTB 2.0 and report the state-of-the-art results in the extraction of the full relation. This is the first time when a model outperforms the knowledge intensive models without employing any linguistic features.