# FAQ Retrieval using Query-Question Similarity and BERT-Based Query-Answer Relevance

arXiv: https://arxiv.org/abs/1905.02851 · HTML: https://mlsanity.com/paper/1905.02851/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 May 2019.

## Built on by (most cited first, 25 of 25)

- [MFAQ: a Multilingual FAQ Dataset](https://mlsanity.com/paper/2109.12870/) (2021)
- [Neural ranking models for document retrieval](https://mlsanity.com/paper/2102.11903/) (2021)
- [Bringing order into the realm of Transformer-based language models for artificial intelligence and law](https://mlsanity.com/paper/2308.05502/) (2023)
- [Time Series Language Model for Descriptive Caption Generation](https://mlsanity.com/paper/2501.01832/) (2025)
- [DAME: Domain Adaptation for Matching Entities](https://mlsanity.com/paper/2204.09244/) (2022)
- [Pre-training Universal Language Representation](https://mlsanity.com/paper/2105.14478/) (2021)
- [Interactive Question Answering Systems: Literature Review](https://mlsanity.com/paper/2209.01621/) (2022)
- [Pre-training with Large Language Model-based Document Expansion for Dense Passage Retrieval](https://mlsanity.com/paper/2308.08285/) (2023)
- [Generate-then-Retrieve: Intent-Aware FAQ Retrieval in Product Search](https://mlsanity.com/paper/2306.03411/) (2023)
- [QUADRo: Dataset and Models for QUestion-Answer Database Retrieval](https://mlsanity.com/paper/2304.01003/) (2023)
- [KisanQRS: A Deep Learning-based Automated Query-Response System for Agricultural Decision-Making](https://mlsanity.com/paper/2411.08883/) (2024)
- [Absformer: Transformer-based Model for Unsupervised Multi-Document Abstractive Summarization](https://mlsanity.com/paper/2306.04787/) (2023)
- [PromptCOS: Towards Content-only System Prompt Copyright Auditing for LLMs](https://mlsanity.com/paper/2509.03117/) (2025)
- [Applying Transfer Learning for Improving Domain-Specific Search Experience Using Query to Question Similarity](https://mlsanity.com/paper/2101.02351/) (2021)
- [Towards More Robust Natural Language Understanding](https://mlsanity.com/paper/2112.02992/) (2021)
- [Enhancing ID-based Recommendation with Large Language Models](https://mlsanity.com/paper/2411.02041/) (2024)
- [ConveRT for FAQ Answering](https://mlsanity.com/paper/2108.00719/) (2021)
- [Multi-Tenant Optimization For Few-Shot Task-Oriented FAQ Retrieval](https://mlsanity.com/paper/2301.10517/) (2023)
- [MFBE: Leveraging Multi-Field Information of FAQs for Efficient Dense Retrieval](https://mlsanity.com/paper/2302.11953/) (2023)
- [TeleDoCTR: Domain-Specific and Contextual Troubleshooting for Telecommunications](https://mlsanity.com/paper/2601.00691/) (2026)
- [Towards Handling Unconstrained User Preferences in Dialogue](https://mlsanity.com/paper/2109.08650/) (2021)
- [Building a Question Answering System for the Manufacturing Domain](https://mlsanity.com/paper/2111.10044/) (2021)
- [Portuguese FAQ for Financial Services](https://mlsanity.com/paper/2311.11331/) (2023)
- [Nepali Passport Question Answering: A Low-Resource Dataset for Public Service Applications](https://mlsanity.com/paper/2603.13320/) (2026)
- [Staged Linguistic Seeding: Grounded Query Expansion for Verified-Unit QA in AI Contact Centers](https://mlsanity.com/paper/2609.00844/) (2026)

## Abstract (arXiv)

Frequently Asked Question (FAQ) retrieval is an important task where the objective is to retrieve an appropriate Question-Answer (QA) pair from a database based on a user's query. We propose a FAQ retrieval system that considers the similarity between a user's query and a question as well as the relevance between the query and an answer. Although a common approach to FAQ retrieval is to construct labeled data for training, it takes annotation costs. Therefore, we use a traditional unsupervised information retrieval system to calculate the similarity between the query and question. On the other hand, the relevance between the query and answer can be learned by using QA pairs in a FAQ database. The recently-proposed BERT model is used for the relevance calculation. Since the number of QA pairs in FAQ page is not enough to train a model, we cope with this issue by leveraging FAQ sets that are similar to the one in question. We evaluate our approach on two datasets. The first one is localgovFAQ, a dataset we construct in a Japanese administrative municipality domain. The second is StackExchange dataset, which is the public dataset in English. We demonstrate that our proposed method outperforms baseline methods on these datasets.