Open-domain Dialogue Generation Grounded with Dynamic Multi-form Knowledge Fusion

by   Feifei Xu, et al.

Open-domain multi-turn conversations normally face the challenges of how to enrich and expand the content of the conversation. Recently, many approaches based on external knowledge are proposed to generate rich semantic and information conversation. Two types of knowledge have been studied for knowledge-aware open-domain dialogue generation: structured triples from knowledge graphs and unstructured texts from documents. To take both advantages of abundant unstructured latent knowledge in the documents and the information expansion capabilities of the structured knowledge graph, this paper presents a new dialogue generation model, Dynamic Multi-form Knowledge Fusion based Open-domain Chatt-ing Machine (DMKCM).In particular, DMKCM applies an indexed text (a virtual Knowledge Base) to locate relevant documents as 1st hop and then expands the content of the dialogue and its 1st hop using a commonsense knowledge graph to get apposite triples as 2nd hop. To merge these two forms of knowledge into the dialogue effectively, we design a dynamic virtual knowledge selector and a controller that help to enrich and expand knowledge space. Moreover, DMKCM adopts a novel dynamic knowledge memory module that effectively uses historical reasoning knowledge to generate better responses. Experimental results indicate the effectiveness of our method in terms of dialogue coherence and informativeness.


page 1

page 2

page 3

page 4


Knowledge Aware Conversation Generation with Reasoning on Augmented Graph

Two types of knowledge, factoid knowledge from graphs and non-factoid kn...

Knowledge Aware Conversation Generation with Explainable Reasoning on Augmented Graphs

Two types of knowledge, triples from knowledge graphs and texts from uns...

RT-KGD: Relation Transition Aware Knowledge-Grounded Dialogue Generation

Grounding dialogue system with external knowledge is a promising way to ...

DialoKG: Knowledge-Structure Aware Task-Oriented Dialogue Generation

Task-oriented dialogue generation is challenging since the underlying kn...

DyKgChat: Benchmarking Dialogue Generation Grounding on Dynamic Knowledge Graphs

Data-driven, knowledge-grounded neural conversation models are capable o...

Constructing a Knowledge Graph from Unstructured Documents without External Alignment

Knowledge graphs (KGs) are relevant to many NLP tasks, but building a re...

RHO (ρ): Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding

Dialogue systems can leverage large pre-trained language models and know...

Please sign up or login with your details

Forgot password? Click here to reset