Conversational Search with Mixed-Initiative - Asking Good Clarification Questions backed-up by Passage Retrieval

Abstract

We deal with the scenario of conversational search, where user queries are under-specified or ambiguous. This calls for a mixed-initiative setup. User-asks (queries) and system-answers, as well as system-asks (clarification questions) and user response, in order to clarify her information needs. We focus on the task of selecting the next clarification question, given the conversation context. Our method leverages passage retrieval from a background content to fine-tune two deep-learning models for ranking candidate clarification questions. We evaluated our method on two different use-cases. The first is an open domain conversational search in a large web collection. The second is a taskoriented customer-support setup. We show that our method performs well on both use-cases.

Dynamic Contexts for Generating Suggestion Questions in RAG Based Conversational Systems

“…However, this concept is closely related to question generation [5] and clarification question generation [3,6]. The concept of clarification questions was formally introduced in [7], and since then, research into generating these questions has spanned a wide range of scenarios, including open-domain systems (AmbigQA) [8], knowledge bases (CLAQUA) [6], closed-book systems (CLAM) [9], information-seeking (ISEEQ) [10], task-oriented dialog systems (CLARIT) [3], and conversational search [11]. Rahmani et al [12] surveyed the various methodologies, datasets, and different evaluation strategies used for clarification questions.…”

“…The distinct characteristics of RAGs [13] make them essential for effective information retrieval and is widely used for generating question-answering tasks [1] and clarification questions [10,11].…”