Semantic Role Labeling Guided Multi-turn Dialogue ReWriter
Kun Xu, Haochen Tan, Linfeng Song, Han Wu, Haisong Zhang, Linqi Song, Dong Yu
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 stateof-the-art systems.
Topics & Concepts
Computer scienceRewritingFocus (optics)Dialog boxContext (archaeology)Core (optical fiber)Natural language processingSemantic role labelingArtificial intelligenceHuman–computer interactionWorld Wide WebProgramming languageOpticsTelecommunicationsSentencePhysicsBiologyPaleontologyTopic ModelingSpeech and dialogue systemsNatural Language Processing Techniques