UniGDD: A Unified Generative Framework for Goal-Oriented Document-Grounded Dialogue
The goal-oriented document-grounded dialogue aims at responding to the user query based on the dialogue context and supporting document. Existing studies tackle this problem by decomposing it into two sub-tasks: knowledge identification and response generation. However, such pipeline methods would unavoidably suffer from the error propagation issue. This paper proposes to unify these two sub-tasks via sequentially generating the grounding knowledge and the response. We further develop a prompt-connected multi-task learning strategy to model the characteristics and connections of different tasks and introduce linear temperature scheduling to reduce the negative effect of irrelevant document information. Experimental results demonstrate the effectiveness of our framework.
Code (1)
Tasks
Multi-Task LearningResponse GenerationSchedulingSimilar Papers 제목 키워드 기반
Variational Hierarchical Dialog Autoencoder for Dialog State Tracking Data Augmentation
Recent works have shown that generative data augmentation, where synthetic samples generated from deep generative models complement the training dataset, benefit NLP tasks. In this work, we extend this approach to the ta…
Data Augmentationdialog state trackingDialogue State TrackingResponse Generation+2A Unified Taxonomy of Deep Syntactic Relations
This paper analyzes multiple deep-syntactic frameworks with the goal of creating a proposal for a set of universal semantic role labels. The proposal examines various theoretic linguistic perspectives and focuses on Mean…
Making Sense of Meaning: A Survey on Metrics for Semantic and Goal-Oriented Communication
Semantic communication (SemCom) aims to convey the meaning behind a transmitted message by transmitting only semantically-relevant information. This semantic-centric design helps to minimize power usage, bandwidth consum…
Semantic CommunicationDiffusion-based Generation, Optimization, and Planning in 3D Scenes
We introduce SceneDiffuser, a conditional generative model for 3D scene understanding. SceneDiffuser provides a unified model for solving scene-conditioned generation, optimization, and planning. In contrast to prior wor…
DenoisingGrasp GenerationMotion GenerationMotion Planning+1NavArena: Automated Construction of Goal-Oriented Navigation Benchmarks from 3D Gaussian Splatting Reconstructions
Fixed 3D Gaussian Splatting (3DGS) reconstructions provide realistic novel views but lack the traversability constraints, valid goals, and closed-loop protocols required for navigation evaluation. We introduce NavArena, …
Visual Navigation