AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Models

Abstract

Attention-based pre-trained language models such as GPT-2 brought considerable progress to end-to-end dialogue modelling. However, they also present considerable risks for task-oriented dialogue, such as lack of knowledge grounding or diversity. To address these issues, we introduce modified training objectives for language model finetuning, and we employ massive data augmentation via back-translation to increase the diversity of the training data. We further examine the possibilities of combining data from multiples sources to improve performance on the target dataset. We carefully evaluate our contributions with both human and automatic methods. Our model substantially outperforms the baseline on the MultiWOZ data and shows competitive performance with state of the art in both automatic and human evaluation.

References in corpus (10)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Sequence to Sequence Learning with Neural Networks
• Decoupled Weight Decay Regularization
• Mixed Precision Training
• Stochastic Language Generation in Dialogue using Recurrent Neural Networks with Convolutional Sentence Reranking
• Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset
• Sequence-to-Sequence Learning for Task-oriented Dialogue with Dialogue State Representation
• Improving Robustness of Task Oriented Dialog Systems
• ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems
• ELITR Non-Native Speech Translation at IWSLT 2020

Cited by in corpus (2)

• Joint System-Wise Optimization for Pipeline Goal-Oriented Dialog System
• Variational Latent-State GPT for Semi-Supervised Task-Oriented Dialog Systems