Dense Template Retrieval for Customer Support

Tiago Mesquita, Bruno Martins, Mariana Almeida


Abstract
Templated answers are used extensively in customer support scenarios, providing an efficient way to cover a plethora of topics, with an easily maintainable collection of templates. However, the number of templates is often too high for an agent to manually search. Automatically suggesting the correct template for a given question can thus improve the service efficiency, reducing costs and leading to a better customer satisfaction. In this work, we propose a dense retrieval framework for the customer support scenario, adapting a standard in-batch negatives technique to support unpaired sampling of queries and templates. We also propose a novel loss that extends the typical query-centric similarity, exploiting other similarity relations in the training data. Experiments show that our approach achieves considerable improvements, in terms of performance and training speed, over more standard dense retrieval methods. This includes methods such as DPR, and also ablated versions of the proposed approach.
Anthology ID:
2022.coling-1.94
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
1106–1115
Language:
URL:
https://aclanthology.org/2022.coling-1.94
DOI:
Bibkey:
Cite (ACL):
Tiago Mesquita, Bruno Martins, and Mariana Almeida. 2022. Dense Template Retrieval for Customer Support. In Proceedings of the 29th International Conference on Computational Linguistics, pages 1106–1115, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Dense Template Retrieval for Customer Support (Mesquita et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.94.pdf