# Matching Questions and Answers in Dialogues from Online Forums

arXiv: https://arxiv.org/abs/2005.09276 · HTML: https://mlsanity.com/paper/2005.09276/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 May 2020.

## Built on by (most cited first, 4 of 4)

- [DialogQAE: N-to-N Question Answer Pair Extraction from Customer Service Chatlog](https://mlsanity.com/paper/2212.07112/) (2022)
- [Universal Model in Online Customer Service](https://mlsanity.com/paper/2402.15666/) (2024)
- [SmartSales: Sales Script Extraction and Analysis from Sales Chatlog](https://mlsanity.com/paper/2204.08811/) (2022)
- [A Diverse and Effective Retrieval-Based Debt Collection System with Expert Knowledge](https://mlsanity.com/paper/2504.06273/) (2025)

## Abstract (arXiv)

Matching question-answer relations between two turns in conversations is not only the first step in analyzing dialogue structures, but also valuable for training dialogue systems. This paper presents a QA matching model considering both distance information and dialogue history by two simultaneous attention mechanisms called mutual attention. Given scores computed by the trained model between each non-question turn with its candidate questions, a greedy matching strategy is used for final predictions. Because existing dialogue datasets such as the Ubuntu dataset are not suitable for the QA matching task, we further create a dataset with 1,000 labeled dialogues and demonstrate that our proposed model outperforms the state-of-the-art and other strong baselines, particularly for matching long-distance QA pairs.