AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Models
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.
PDF Abstract EMNLP (NLP4ConvAI) 2021 PDF EMNLP (NLP4ConvAI) 2021 AbstractCode
Datasets
MultiWOZ
Taskmaster-1
Results from the Paper
Ranked #3 on
End-To-End Dialogue Modelling
on MULTIWOZ 2.0
(using extra training data)
