Social Commonsense-Guided Search Query Generation for Open-Domain Knowledge-Powered Conversations
Submission Type: Regular Short Paper
Submission Track: Dialogue and Interactive Systems
Submission Track 2: Discourse and Pragmatics
Keywords: Conversational AI, Knowledge-Powered Dialog, Commonsense Knowledge
TL;DR: To tackle passive conversations, we propose to integrate social commonsense reasoning for the generation of search queries in knowledge-powered conversations.
Abstract: Open-domain dialog involves generating search queries that help obtain relevant knowledge for holding informative conversations. However, it can be challenging to determine what information to retrieve when the user is passive and does not express a clear need or request. To tackle this issue, we present a novel approach that focuses on generating internet search queries that are guided by social commonsense. Specifically, we leverage a commonsense dialog system to establish connections related to the conversation topic, which subsequently guides our query generation. Our proposed framework addresses passive user interactions by integrating topic tracking, commonsense response generation and instruction-driven query generation. Through extensive evaluations, we show that our approach overcomes limitations of existing query generation techniques that rely solely on explicit dialog information, and produces search queries that are more relevant, specific, and compelling, ultimately resulting in more engaging responses.
Submission Number: 4159
Loading