Conversational Machine Comprehension: a Literature Review

Proceedings of the 28th International Conference on Computational Linguistics, pages 2739–2753 Barcelona, Spain (Online), December 8-13, 2020 2739 Conversational Machine Comprehension: a Literature Review Somil Gupta CICS, UMass Amherst somilgupta@umass.edu Bhanu Pratap Singh Rawat CICS, UMass Amherst brawat@umass.edu Hong Yu CICS, UMass Lowell Hong Yu@uml.edu Abstract Conversational Machine Comprehension (CMC), a research track in conversational AI, expects the machine to understand an open-domain natural language text and thereafter engage in a multi-turn conversation to answer questions related to the text. While most of the research in Machine Reading Comprehension (MRC) revolves around single-turn question answering (QA), multi-turn CMC has recently gained prominence, thanks to the advancement in natural language understanding via neural language models such as BERT and the introduction of large-scale con- versational datasets such as CoQA and QuAC. The rise in interest has, however, led to a flurry of concurrent publications, each with a different yet structurally similar modeling approach and an inconsistent view of the surrounding literature. With the volume of model submissions to conver- sational datasets increasing every year, there exists a need to consolidate the scattered knowledge in this domain to streamline future research. This literature review attempts at providing a holis- tic overview of CMC with an emphasis on the common trends across recently published models, specifically in their approach to tackling conversational history. The review synthesizes a generic framework for CMC models while highlighting the differences in recent approaches and intends to serve as a compendium of CMC for future researchers. 1 Introduction Developing open-domain, intelligent dialog systems that can satisfactorily interact like humans, perform complex tasks and/or answer on a range of topics has been one of the most ambitious and difficult goals in Artificial Intelligence (AI). The study of such systems, called Conversational AI (ConvAI), is at the confluence of Natural language Processing (NLP), Information Retrieval (IR), and Machine Learning (ML), attracting significant research from both academia and industry. The recent developments in Deep Learning (DL) (Du and Black, 2019; Hatua et al., 2019) and Reinforcement Learning (RL) (Lipton et al., 2016; Peng et al., 2018) have further boosted research in the domain, making it one of the most sought after research topics in AI. Based on the nature of problems, a ConvAI system is expected to solve three major research problems (Gao et al., 2018). Question Answering (QA) involves providing answers to user queries through con- versation, using the knowledge drawn from various data sources like a snippet from a text, a collection of web documents, or an entire knowledge base. Task completion expects the conversational agent to accomplish task/s for the user, using the information acquired through conversation. Finally, Social Chat makes the agent emulate humans and converse seamlessly and appropriately with users, as in the Turing test (Saygin et al., 2000). Each of these fields has its own set of challenges to tackle. Challenges in QA can vary depending on the source of knowledge, the answer extraction strategy em- ployed, and the domain of the question. Machine Reading …

Content truncated to 500 words