A Hybrid Task-Oriented Dialog System with Domain and Task Adaptive Pretraining
arXiv:2102.04506
Abstract
This paper describes our submission for the End-to-end Multi-domain Task Completion Dialog shared task at the 9th Dialog System Technology Challenge (DSTC-9). Participants in the shared task build an end-to-end task completion dialog system which is evaluated by human evaluation and a user simulator based automatic evaluation. Different from traditional pipelined approaches where modules are optimized individually and suffer from cascading failure, we propose an end-to-end dialog system that 1) uses Generative Pretraining 2 (GPT-2) as the backbone to jointly solve Natural Language Understanding, Dialog State Tracking, and Natural Language Generation tasks, 2) adopts Domain and Task Adaptive Pretraining to tailor GPT-2 to the dialog domain before finetuning, 3) utilizes heuristic pre/post-processing rules that greatly simplify the prediction tasks and improve generalizability, and 4) equips a fault tolerance module to correct errors and inappropriate responses. Our proposed method significantly outperforms baselines and ties for first place in the official evaluation. We make our source code publicly available.
References in corpus (10)
- HuggingFace's Transformers: State-of-the-art Natural Language Processing
- Rasa: Open Source Language Understanding and Dialogue Management
- SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teaching
- Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset
- Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context
- Dialog State Tracking: A Neural Reading Comprehension Approach
- Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models
- ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems
- MultiWOZ 2.1: A Consolidated Multi-Domain Dialogue Dataset with State Corrections and State Tracking Baselines
- Conditional Generation and Snapshot Learning in Neural Dialogue Systems