Conversation Graph: Data Augmentation, Training, and Evaluation for Non-Deterministic Dialogue Management

Milan Gritta, Gerasimos Lampouras, Ignacio Iacobacci


Abstract
Task-oriented dialogue systems typically rely on large amounts of high-quality training data or require complex handcrafted rules. However, existing datasets are often limited in size con- sidering the complexity of the dialogues. Additionally, conventional training signal in- ference is not suitable for non-deterministic agent behavior, namely, considering multiple actions as valid in identical dialogue states. We propose the Conversation Graph (ConvGraph), a graph-based representation of dialogues that can be exploited for data augmentation, multi- reference training and evaluation of non- deterministic agents. ConvGraph generates novel dialogue paths to augment data volume and diversity. Intrinsic and extrinsic evaluation across three datasets shows that data augmentation and/or multi-reference training with ConvGraph can improve dialogue success rates by up to 6.4%.
Anthology ID:
2021.tacl-1.3
Volume:
Transactions of the Association for Computational Linguistics, Volume 9
Month:
Year:
2021
Address:
Cambridge, MA
Editors:
Brian Roark, Ani Nenkova
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
36–52
Language:
URL:
https://aclanthology.org/2021.tacl-1.3
DOI:
10.1162/tacl_a_00352
Bibkey:
Cite (ACL):
Milan Gritta, Gerasimos Lampouras, and Ignacio Iacobacci. 2021. Conversation Graph: Data Augmentation, Training, and Evaluation for Non-Deterministic Dialogue Management. Transactions of the Association for Computational Linguistics, 9:36–52.
Cite (Informal):
Conversation Graph: Data Augmentation, Training, and Evaluation for Non-Deterministic Dialogue Management (Gritta et al., TACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.tacl-1.3.pdf
Video:
 https://aclanthology.org/2021.tacl-1.3.mp4