A Survey of Ontology Expansion for Conversational Understanding
Jinggui Liang, Yuxia Wu, Yuan Fang, Hao Fei, and Lizi Liao

TL;DR
This survey reviews recent techniques in Ontology Expansion for conversational AI, focusing on new intent and slot discovery to improve agent adaptability and robustness in real-world interactions.
Contribution
It categorizes existing OnExp methods into three areas and highlights emerging challenges and frontiers for enhancing conversational understanding.
Findings
Identifies key categories: New Intent Discovery, New Slot-Value Discovery, Joint OnExp.
Analyzes methodologies and benchmarks in OnExp.
Discusses challenges and future directions in ontology expansion.
Abstract
In the rapidly evolving field of conversational AI, Ontology Expansion (OnExp) is crucial for enhancing the adaptability and robustness of conversational agents. Traditional models rely on static, predefined ontologies, limiting their ability to handle new and unforeseen user needs. This survey paper provides a comprehensive review of the state-of-the-art techniques in OnExp for conversational understanding. It categorizes the existing literature into three main areas: (1) New Intent Discovery, (2) New Slot-Value Discovery, and (3) Joint OnExp. By examining the methodologies, benchmarks, and challenges associated with these areas, we highlight several emerging frontiers in OnExp to improve agent performance in real-world scenarios and discuss their corresponding challenges. This survey aspires to be a foundational reference for researchers and practitioners, promoting further…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
Taxonomy
TopicsSpeech and dialogue systems · Advanced Text Analysis Techniques · Semantic Web and Ontologies
MethodsOntology
