Unleashing the Power of Neural Discourse Parsers -- A Context and Structure Aware Approach Using Large Scale Pretraining

TL;DR

This paper introduces a highly accurate neural discourse parser that leverages large-scale pretraining and contextual language models, achieving state-of-the-art results in RST discourse parsing tasks.

Contribution

The paper presents a simple yet effective neural discourse parser that incorporates large-scale pretraining on a new discourse treebank, setting new performance benchmarks.

Findings

Achieves state-of-the-art performance on RST-DT and Instr-DT datasets.

Pretraining on MEGA-DT significantly improves parsing accuracy.

Demonstrates the effectiveness of large-scale pretraining in discourse parsing.

Abstract

RST-based discourse parsing is an important NLP task with numerous downstream applications, such as summarization, machine translation and opinion mining. In this paper, we demonstrate a simple, yet highly accurate discourse parser, incorporating recent contextual language models. Our parser establishes the new state-of-the-art (SOTA) performance for predicting structure and nuclearity on two key RST datasets, RST-DT and Instr-DT. We further demonstrate that pretraining our parser on the recently available large-scale "silver-standard" discourse treebank MEGA-DT provides even larger performance benefits, suggesting a novel and promising research direction in the field of discourse analysis.