Multi-Tenant Optimization For Few-Shot Task-Oriented FAQ Retrieval
Not on the map. Why?
Abstract (arXiv)
Business-specific Frequently Asked Questions (FAQ) retrieval in task-oriented dialog systems poses unique challenges vis-`a-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 switching.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 18 of its 26 references that are in the map. First posted on arXiv 25 Jan 2023.
Builds on
18 of 26 references.
References · 18
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
- 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,548
- 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
- 2020Recipes for building an open-domain chatbotcited by 593
- 2020Efficient Intent Detection with Dual Sentence Encoderscited by 419
- 2019An Evaluation Dataset for Intent Classification and Out-of-Scope Predictioncited by 378
- 2020On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselinescited by 254
- 2018Sentence Encoders on STILTs: Supplementary Training on Intermediate Labeled-data Taskscited by 214
- 2019Benchmarking Natural Language Understanding Services for building Conversational Agentscited by 166
- 2021GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrievalcited by 119
6 more
- 2020DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialoguecited by 89
- 2020Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inferencecited by 47
- 2021Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuningcited by 46
- 2021Effectiveness of Pre-training for Few-shot Intent Classificationcited by 27
- 2019FAQ Retrieval using Query-Question Similarity and BERT-Based Query-Answer Relevancecited by 24
- 2020HINT3: Raising the bar for Intent Detection in the Wildcited by 21
Built on by
Citing papers per year: 2025: 1.
1 paper.