Semantic Role Labeling Guided Multi-turn Dialogue ReWriter

by   Kun Xu, et al.

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.


page 1

page 2

page 3

page 4


Amendable Generation for Dialogue State Tracking

In task-oriented dialogue systems, recent dialogue state tracking method...

Knowledge Augmented BERT Mutual Network in Multi-turn Spoken Dialogues

Modern spoken language understanding (SLU) systems rely on sophisticated...

Speaker Role Contextual Modeling for Language Understanding and Dialogue Policy Learning

Language understanding (LU) and dialogue policy learning are two essenti...

Copy-Enhanced Heterogeneous Information Learning for Dialogue State Tracking

Dialogue state tracking (DST) is an essential component in task-oriented...

CSAGN: Conversational Structure Aware Graph Network for Conversational Semantic Role Labeling

Conversational semantic role labeling (CSRL) is believed to be a crucial...

Improving Response Selection in Multi-turn Dialogue Systems

Building systems that can communicate with humans is a core problem in A...

"The Boating Store Had Its Best Sail Ever": Pronunciation-attentive Contextualized Pun Recognition

Humor plays an important role in human languages and it is essential to ...