Abstract
Business-specific Frequently Asked Questions (FAQ) retrieval in task-oriented dialog systems poses unique challenges vis-à-vis community based FAQs. Each FAQ question represents an intent which is usually an umbrella term for many related user queries. We evaluate performance for such Business FAQs both with standard FAQ retrieval techniques using query-Question (q-Q) similarity and few-shot intent detection techniques. Implementing a real-world solution for FAQ retrieval in order to support multiple tenants (FAQ sets) entails optimizing speed, accuracy and cost. We propose a novel approach to scale multi-tenant FAQ applications in real-world context by contrastive fine-tuning of the last layer in sentence Bi-Encoders along with tenant-specific weight switching1
Cite
CITATION STYLE
Vishwanathan, A., Warrier, R. U., Suresh, G. V., & Kandpal, C. S. (2022). Multi-Tenant Optimization For Few-Shot Task-Oriented FAQ Retrieval. In EMNLP 2022 - Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track (pp. 198–207). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2022.emnlp-industry.19
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
