Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Survey of Ontology Expansion for Conversational Understanding

Jinggui Liang, Yuxia Wu, Yuan Fang, Hao Fei, Lizi Liao

TL;DR

This survey paper provides a comprehensive review of the state-of-the-art techniques in OnExp for conversational understanding, and categorizes the existing literature into three main areas: (1) New Intent Discovery, (2) New Slot-Value Discovery, and (3) Joint OnExp.

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 exploration and innovation in this crucial domain.

A Survey of Ontology Expansion for Conversational Understanding

TL;DR

This survey paper provides a comprehensive review of the state-of-the-art techniques in OnExp for conversational understanding, and categorizes the existing literature into three main areas: (1) New Intent Discovery, (2) New Slot-Value Discovery, and (3) Joint OnExp.

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 exploration and innovation in this crucial domain.

Paper Structure

This paper contains 49 sections, 10 equations, 2 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Preliminaries
  3. Task Formulation
  4. Data Resources
  5. Evaluation Protocols
  6. NID Metrics.
  7. NSVD Metrics.
  8. Other Metrics.
  9. Taxonomy of OnExp Research
  10. New Intent Discovery
  11. Unsupervised NID
  12. Rule-based Methods.
  13. Statistical Methods.
  14. NN-based Methods.
  15. Zero-shot NID.
  16. ...and 34 more sections

Figures (2)

  • Figure 1: An example of ontology expansion enabling conversational agents to adapt to unseen events.
  • Figure 2: The taxonomy for Ontology Expansion.