Conversational question answering: a survey

TLDR

Question answering systems enable querying structured and unstructured data in natural language and form a core component of conversational AI, where recent focus has shifted from single‑turn to multi‑turn interactions supported by large datasets and pretrained models. This survey aims to comprehensively review recent state‑of‑the‑art research trends in conversational question answering. The authors analyze and synthesize findings from recent papers to map the evolution of CQA methods and datasets. The review reveals a clear shift toward multi‑turn QA, highlighting its growing importance and providing a foundation for future research in conversational AI.

Abstract

Abstract Question answering (QA) systems provide a way of querying the information available in various formats including, but not limited to, unstructured and structured data in natural languages. It constitutes a considerable part of conversational artificial intelligence (AI) which has led to the introduction of a special research topic on conversational question answering (CQA), wherein a system is required to understand the given context and then engages in multi-turn QA to satisfy a user’s information needs. While the focus of most of the existing research work is subjected to single-turn QA, the field of multi-turn QA has recently grasped attention and prominence owing to the availability of large-scale, multi-turn QA datasets and the development of pre-trained language models. With a good amount of models and research papers adding to the literature every year recently, there is a dire need of arranging and presenting the related work in a unified manner to streamline future research. This survey is an effort to present a comprehensive review of the state-of-the-art research trends of CQA primarily based on reviewed papers over the recent years. Our findings show that there has been a trend shift from single-turn to multi-turn QA which empowers the field of Conversational AI from different perspectives. This survey is intended to provide an epitome for the research community with the hope of laying a strong foundation for the field of CQA.