Deploying a Retrieval based Response Model for Task Oriented Dialogues

Lahari Poddar, György Szarvas, Cheng Wang, Jorge Balazs, Pavel Danchenko, Patrick Ernst

Abstract
Task-oriented dialogue systems in industry settings need to have high conversational capability, be easily adaptable to changing situations and conform to business constraints. This paper describes a 3-step procedure to develop a conversational model that satisfies these criteria and can efficiently scale to rank a large set of response candidates. First, we provide a simple algorithm to semi-automatically create a high-coverage template set from historic conversations without any annotation. Second, we propose a neural architecture that encodes the dialogue context and applicable business constraints as profile features for ranking the next turn. Third, we describe a two-stage learning strategy with self-supervised training, followed by supervised fine-tuning on limited data collected through a human-in-the-loop platform. Finally, we describe offline experiments and present results of deploying our model with human-in-the-loop to converse with live customers online.
Anthology ID:
2022.emnlp-industry.17
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track
Month:
December
Year:
2022
Address:
Abu Dhabi, UAE
Editors:
Yunyao Li, Angeliki Lazaridou
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
169–178
Language:
URL:
https://aclanthology.org/2022.emnlp-industry.17
DOI:
10.18653/v1/2022.emnlp-industry.17
Bibkey:
Cite (ACL):
Lahari Poddar, György Szarvas, Cheng Wang, Jorge Balazs, Pavel Danchenko, and Patrick Ernst. 2022. Deploying a Retrieval based Response Model for Task Oriented Dialogues. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 169–178, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
Deploying a Retrieval based Response Model for Task Oriented Dialogues (Poddar et al., EMNLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl-24-ws-corrections/2022.emnlp-industry.17.pdf
PDF Search