Unstructured Text Enhanced Open-domain Dialogue System: A Systematic Survey

Abstract

Incorporating external knowledge into dialogue generation has been proven to benefit the performance of an open-domain Dialogue System (DS), such as generating informative or stylized responses, controlling conversation topics. In this article, we study the open-domain DS that uses unstructured text as external knowledge sources (\textbf{U}nstructured \textbf{T}ext \textbf{E}nhanced \textbf{D}ialogue \textbf{S}ystem, \textbf{UTEDS}). The existence of unstructured text entails distinctions between UTEDS and traditional data-driven DS and we aim to analyze these differences. We first give the definition of the UTEDS related concepts, then summarize the recently released datasets and models. We categorize UTEDS into Retrieval and Generative models and introduce them from the perspective of model components. The retrieval models consist of Fusion, Matching, and Ranking modules, while the generative models comprise Dialogue and Knowledge Encoding, Knowledge Selection, and Response Generation modules. We further summarize the evaluation methods utilized in UTEDS and analyze the current models' performance. At last, we discuss the future development trends of UTEDS, hoping to inspire new research in this field.

45 pages, 3 Figures, 11 Tables

References in corpus (17)

• A Survey on Knowledge Graphs: Representation, Acquisition and Applications
• Knowledge Graphs
• A Review of Relational Machine Learning for Knowledge Graphs
• Pre-trained Models for Natural Language Processing: A Survey
• A Deep Relevance Matching Model for Ad-hoc Retrieval
• Wizard of Wikipedia: Knowledge-Powered Conversational agents
• A Survey on Dialogue Systems: Recent Advances and New Frontiers
• ReasoNet: Learning to Stop Reading in Machine Comprehension
• TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents
• Survey on Evaluation Methods for Dialogue Systems
• Response Ranking with Deep Matching Networks and External Knowledge in Information-seeking Conversation Systems
• Interaction Embeddings for Prediction and Explanation in Knowledge Graphs
• From Eliza to XiaoIce: Challenges and Opportunities with Social Chatbots
• Challenges in Building Intelligent Open-domain Dialog Systems
• Introducing MANtIS: a novel Multi-Domain Information Seeking Dialogues Dataset
• Improving Conditioning in Context-Aware Sequence to Sequence Models
• Knowledge-Grounded Response Generation with Deep Attentional Latent-Variable Model