Semantic Role Labeling Guided Multi-turn Dialogue ReWriter

TL;DR

This paper introduces a semantic role labeling guided approach to enhance multi-turn dialogue rewriting by focusing on core semantic information, significantly improving model performance.

Contribution

It proposes integrating semantic role labeling into dialogue rewriting models to better capture essential semantic information and reduce noise, advancing the state-of-the-art.

Findings

Semantic role labeling improves dialogue rewriting accuracy.

The SRL-guided model outperforms previous state-of-the-art systems.

Enhanced focus on core semantic roles leads to better contextual understanding.

Abstract

For multi-turn dialogue rewriting, the capacity of effectively modeling the linguistic knowledge in dialog context and getting rid of the noises is essential to improve its performance. Existing attentive models attend to all words without prior focus, which results in inaccurate concentration on some dispensable words. In this paper, we propose to use semantic role labeling (SRL), which highlights the core semantic information of who did what to whom, to provide additional guidance for the rewriter model. Experiments show that this information significantly improves a RoBERTa-based model that already outperforms previous state-of-the-art systems.