Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Neural-Bayesian Program Learning for Few-shot Dialogue Intent Parsing

Mengze Hong, Di Jiang, Yuanfeng Song, Chen Jason Zhang

TL;DR

Experimental results demonstrate that DI-Parser outperforms state-of-the-art deep learning models and offers practical advantages for industrial-scale applications.

Abstract

With the growing importance of customer service in contemporary business, recognizing the intents behind service dialogues has become essential for the strategic success of enterprises. However, the nature of dialogue data varies significantly across different scenarios, and implementing an intent parser for a specific domain often involves tedious feature engineering and a heavy workload of data labeling. In this paper, we propose a novel Neural-Bayesian Program Learning model named Dialogue-Intent Parser (DI-Parser), which specializes in intent parsing under data-hungry settings and offers promising performance improvements. DI-Parser effectively utilizes data from multiple sources in a "Learning to Learn" manner and harnesses the "wisdom of the crowd" through few-shot learning capabilities on human-annotated datasets. Experimental results demonstrate that DI-Parser outperforms state-of-the-art deep learning models and offers practical advantages for industrial-scale applications.

Neural-Bayesian Program Learning for Few-shot Dialogue Intent Parsing

TL;DR

Experimental results demonstrate that DI-Parser outperforms state-of-the-art deep learning models and offers practical advantages for industrial-scale applications.

Abstract

With the growing importance of customer service in contemporary business, recognizing the intents behind service dialogues has become essential for the strategic success of enterprises. However, the nature of dialogue data varies significantly across different scenarios, and implementing an intent parser for a specific domain often involves tedious feature engineering and a heavy workload of data labeling. In this paper, we propose a novel Neural-Bayesian Program Learning model named Dialogue-Intent Parser (DI-Parser), which specializes in intent parsing under data-hungry settings and offers promising performance improvements. DI-Parser effectively utilizes data from multiple sources in a "Learning to Learn" manner and harnesses the "wisdom of the crowd" through few-shot learning capabilities on human-annotated datasets. Experimental results demonstrate that DI-Parser outperforms state-of-the-art deep learning models and offers practical advantages for industrial-scale applications.
Paper Structure (18 sections, 8 equations, 1 figure, 2 tables, 1 algorithm)

This paper contains 18 sections, 8 equations, 1 figure, 2 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Bayesian Program Learning
  4. Dialogue Intent Parsing
  5. Methodology
  6. Compositional Components of DI-Parser
  7. Intent
  8. Intent Distribution
  9. Intent Transition
  10. Neural Embedding
  11. Neural-Bayesian Program of DI-Parser
  12. Parsing Dialogues with DI-Parser
  13. Parsing without Learning to Learn
  14. Parsing with Learning to Learn
  15. Experiments
  16. ...and 3 more sections

Figures (1)

  • Figure 1: Graphical model of our proposed DI-Parser, whose learning process is initialized by learning to learn.