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

Jonáš Kulhánek, Vojtěch Hudeček, Tomáš Nekvinda, Ondřej Dušek


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.
Anthology ID:
2021.nlp4convai-1.19
Volume:
Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI
Month:
November
Year:
2021
Address:
Online
Venues:
EMNLP | NLP4ConvAI
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
198–210
Language:
URL:
https://aclanthology.org/2021.nlp4convai-1.19
DOI:
10.18653/v1/2021.nlp4convai-1.19
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.nlp4convai-1.19.pdf
Code
 ufal/augpt
Data
MultiWOZTaskmaster-1