UniGDD: A Unified Generative Framework for Goal-Oriented Document-Grounded Dialogue

04/16/2022
by   Chang Gao, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/10/2021

DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualization

Identifying relevant knowledge to be used in conversational systems that...
research
09/26/2021

MultiDoc2Dial: Modeling Dialogues Grounded in Multiple Documents

We propose MultiDoc2Dial, a new task and dataset on modeling goal-orient...
research
02/13/2023

PK-ICR: Persona-Knowledge Interactive Context Retrieval for Grounded Dialogue

Identifying relevant Persona or Knowledge for conversational systems is ...
research
04/26/2021

Focused Attention Improves Document-Grounded Generation

Document grounded generation is the task of using the information provid...
research
06/14/2021

Cascaded Span Extraction and Response Generation for Document-Grounded Dialog

This paper summarizes our entries to both subtasks of the first DialDoc ...
research
02/23/2023

Coarse-to-Fine Knowledge Selection for Document Grounded Dialogs

Multi-document grounded dialogue systems (DGDS) belong to a class of con...
research
03/30/2021

Grounding Dialogue Systems via Knowledge Graph Aware Decoding with Pre-trained Transformers

Generating knowledge grounded responses in both goal and non-goal orient...

Please sign up or login with your details

Forgot password? Click here to reset