Resource Constrained Dialog Policy Learning Via Differentiable Inductive Logic Programming

Zhenpeng Zhou, Ahmad Beirami, Paul Crook, Pararth Shah, Rajen Subba, Alborz Geramifard


Abstract
Motivated by the needs of resource constrained dialog policy learning, we introduce dialog policy via differentiable inductive logic (DILOG). We explore the tasks of one-shot learning and zero-shot domain transfer with DILOG on SimDial and MultiWoZ. Using a single representative dialog from the restaurant domain, we train DILOG on the SimDial dataset and obtain 99+% in-domain test accuracy. We also show that the trained DILOG zero-shot transfers to all other domains with 99+% accuracy, proving the suitability of DILOG to slot-filling dialogs. We further extend our study to the MultiWoZ dataset achieving 90+% inform and success metrics. We also observe that these metrics are not capturing some of the shortcomings of DILOG in terms of false positives, prompting us to measure an auxiliary Action F1 score. We show that DILOG is 100x more data efficient than state-of-the-art neural approaches on MultiWoZ while achieving similar performance metrics. We conclude with a discussion on the strengths and weaknesses of DILOG.
Anthology ID:
2020.coling-main.597
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
6775–6787
Language:
URL:
https://aclanthology.org/2020.coling-main.597
DOI:
10.18653/v1/2020.coling-main.597
Bibkey:
Cite (ACL):
Zhenpeng Zhou, Ahmad Beirami, Paul Crook, Pararth Shah, Rajen Subba, and Alborz Geramifard. 2020. Resource Constrained Dialog Policy Learning Via Differentiable Inductive Logic Programming. In Proceedings of the 28th International Conference on Computational Linguistics, pages 6775–6787, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
Resource Constrained Dialog Policy Learning Via Differentiable Inductive Logic Programming (Zhou et al., COLING 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2020.coling-main.597.pdf
Data
MultiWOZ