On Task-Level Dialogue Composition of Generative Transformer Model

Prasanna Parthasarathi, Sharan Narang, Arvind Neelakantan


Abstract
Task-oriented dialogue systems help users accomplish tasks such as booking a movie ticket and ordering food via conversation. Generative models parameterized by a deep neural network are widely used for next turn response generation in such systems. It is natural for users of the system to want to accomplish multiple tasks within the same conversation, but the ability of generative models to compose multiple tasks is not well studied. In this work, we begin by studying the effect of training human-human task-oriented dialogues towards improving the ability to compose multiple tasks on Transformer generative models. To that end, we propose and explore two solutions: (1) creating synthetic multiple task dialogue data for training from human-human single task dialogue and (2) forcing the encoder representation to be invariant to single and multiple task dialogues using an auxiliary loss. The results from our experiments highlight the difficulty of even the sophisticated variant of transformer model in learning to compose multiple tasks from single task dialogues.
Anthology ID:
2020.insights-1.6
Volume:
Proceedings of the First Workshop on Insights from Negative Results in NLP
Month:
November
Year:
2020
Address:
Online
Venues:
EMNLP | insights
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
41–47
Language:
URL:
https://www.aclweb.org/anthology/2020.insights-1.6
DOI:
10.18653/v1/2020.insights-1.6
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.insights-1.6.pdf
Optional supplementary material:
 2020.insights-1.6.OptionalSupplementaryMaterial.pdf