Conversational question answering: a survey

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.

Geography of Technology Transfer in China

“…Recently, Large Language Models (LLMs) such as PaLM [2] and GPT family [1,13] have revolutionized the methodology of tackling natural language processing (NLP) tasks such as sentiment analysis [20], question answering [24], text summarization [23], and reasoning on arithmetic and common sense questions [25].…”

A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4

“…Overview. Question Answering (QA) is an important natural language processing task which deals with the development of algorithms to understand and interpret user queries in natural language and then deliver accurate responses [174], [175]. The main aim of question answering systems is to enhance human-computer interaction, i.e., QA systems avoid the use of complex commands and allow the user to interact with machines in a more natural way through natural language queries.…”

A Knowledge-Grounded Task-Oriented Dialogue System with Hierarchical Structure for Enhancing Knowledge Selection

“…Research is actively underway on conversational Artificial Intelligence (AI), which aims not only to successfully mimic human conversations, but also to appropriately provide knowledge-based answers and actions to users’ questions [ 1 , 2 , 3 , 4 ]. A representative conversational AI is the Task-Oriented Dialogue (ToD) system, which focuses on providing the information needed by a given database or API and performing specific actions closely related to real life, such as flight and hotel reservations.…”

“…ToD systems are distinguished from social bots, which aim to provide satisfaction by enabling natural and smooth conversations with humans on various topics based on an open domain [ 1 ]. Therefore, it is important to generate responses using information about the topic of the conversation to better understand the meaning contained in a user’s speech to provide the right service or to respond fluently and accurately to a user’s questions.…”