Matching Questions and Answers in Dialogues from Online Forums
Qi Jia, Mengxue Zhang, Shengyao Zhang, Kenny Q. Zhu

TL;DR
This paper introduces a novel QA matching model for dialogues that leverages mutual attention mechanisms and a new dataset, significantly improving accuracy in matching question-answer pairs, especially over long distances.
Contribution
The paper proposes a new QA matching model with mutual attention and creates a dedicated dataset, outperforming existing methods in dialogue QA matching tasks.
Findings
Model outperforms state-of-the-art baselines.
Effective in matching long-distance QA pairs.
New dataset facilitates better evaluation.
Abstract
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Speech and dialogue systems · Natural Language Processing Techniques
