Link the World: Improving Open-domain Conversation with Dynamic Spatiotemporal-aware Knowledge

TL;DR

This paper introduces a novel dialogue system that leverages spatiotemporal-aware dynamic knowledge and service information to enhance open-domain conversations, significantly improving response quality and consistency.

Contribution

It proposes a new method integrating spatiotemporal dynamic knowledge and service information, along with a new dataset DuSinc, to make dialogue systems more world-aware and human-like.

Findings

Service information improves dialogue consistency and informativeness.

The system's session-level score increased by 60.87% with dynamic knowledge.

The dataset and methods will be open-sourced.

Abstract

Making chatbots world aware in a conversation like a human is a crucial challenge, where the world may contain dynamic knowledge and spatiotemporal state. Several recent advances have tried to link the dialog system to a static knowledge base or search engine, but they do not contain all the world information needed for conversations. In contrast, we propose a new method to improve the dialogue system using spatiotemporal aware dynamic knowledge. We utilize service information as a way for the dialogue system to link the world. The system actively builds a request according to the dialog context and spatiotemporal state to get service information and then generates world aware responses. To implement this method, we collect DuSinc, an open-domain human-human dialogue dataset, where a participant can access the service to get the information needed for dialogue responses. Through automatic and human evaluations, we found that service information significantly improves the consistency, informativeness, factuality, and engagingness of the dialogue system, making it behave more like a human. Compared to the pre-trained models without spatiotemporal aware dynamic knowledge, the overall session-level score was improved by 60.87\%. The collection dataset and methods will be open-sourced.