Resource Constrained Dialog Policy Learning via Differentiable Inductive Logic Programming
arXiv:2011.05457
Abstract
Motivated by the needs of resource constrained dialog policy learning, we introduce dialog policy via differentiable inductive logic (DILOG). We explore the tasks of one-shot learning and zero-shot domain transfer with DILOG on SimDial and MultiWoZ. Using a single representative dialog from the restaurant domain, we train DILOG on the SimDial dataset and obtain 99+% in-domain test accuracy. We also show that the trained DILOG zero-shot transfers to all other domains with 99+% accuracy, proving the suitability of DILOG to slot-filling dialogs. We further extend our study to the MultiWoZ dataset achieving 90+% inform and success metrics. We also observe that these metrics are not capturing some of the shortcomings of DILOG in terms of false positives, prompting us to measure an auxiliary Action F1 score. We show that DILOG is 100x more data efficient than state-of-the-art neural approaches on MultiWoZ while achieving similar performance metrics. We conclude with a discussion on the strengths and weaknesses of DILOG.
References in corpus (12)
- A Simple Language Model for Task-Oriented Dialogue
- SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teaching
- Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset
- Zero-Resource Knowledge-Grounded Dialogue Generation
- Alternating Recurrent Dialog Model with Large-scale Pre-trained Language Models
- ConvLab: Multi-Domain End-to-End Dialog System Platform
- Few-Shot Generalization Across Dialogue Tasks
- Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context
- Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models
- Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention
- Domain Adaptive Dialog Generation via Meta Learning
- Zero-Shot Dialog Generation with Cross-Domain Latent Actions