Semantic Role Labeling Guided Multi-turn Dialogue ReWriter

10/03/2020
by   Kun Xu, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/29/2021

Amendable Generation for Dialogue State Tracking

In task-oriented dialogue systems, recent dialogue state tracking method...
research
02/23/2022

Knowledge Augmented BERT Mutual Network in Multi-turn Spoken Dialogues

Modern spoken language understanding (SLU) systems rely on sophisticated...
research
07/27/2023

Improving Aspect-Based Sentiment with End-to-End Semantic Role Labeling Model

This paper presents a series of approaches aimed at enhancing the perfor...
research
03/31/2023

FCC: Fusing Conversation History and Candidate Provenance for Contextual Response Ranking in Dialogue Systems

Response ranking in dialogues plays a crucial role in retrieval-based co...
research
09/30/2017

Speaker Role Contextual Modeling for Language Understanding and Dialogue Policy Learning

Language understanding (LU) and dialogue policy learning are two essenti...
research
08/21/2019

Copy-Enhanced Heterogeneous Information Learning for Dialogue State Tracking

Dialogue state tracking (DST) is an essential component in task-oriented...
research
09/23/2021

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

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

Please sign up or login with your details

Forgot password? Click here to reset