HintMiner: Automatic Question Hints Mining From Q&A Web Posts with Language Model via Self-Supervised Learning

HintMiner：基于自监督学习与语言模型的问答社区问题提示自动挖掘工具

Abstract: Users often need ask questions and seek answers online. The Question-Answering (QA) forums such as Stack Overflow cannot always respond to the questions timely and properly. In this paper, we propose HintMiner, a novel automatic question hints mining tool for users to help them find answers.

摘要： 用户经常需要在网上提问并寻求答案。像 Stack Overflow 这样的问答（QA）论坛并不总能及时、妥善地回答问题。在本文中，我们提出了 HintMiner，这是一种新颖的自动问题提示挖掘工具，旨在帮助用户寻找答案。

HintMiner leverages the machine comprehension and sequence generation techniques to automatically generate hints for users’ questions. It firstly retrieves many web Q&A posts and then extracts some hints from the posts using MiningNet that is built via a language model.

HintMiner 利用机器理解和序列生成技术，为用户的问题自动生成提示。它首先检索大量的网络问答帖子，然后使用基于语言模型构建的 MiningNet 从这些帖子中提取提示。

Using the huge amount of online Q&A posts, we design a self-supervised objective to train the MiningNet that is a neural encoder-decoder model based on the transformer and copying mechanisms.

利用海量的在线问答帖子，我们设计了一个自监督目标来训练 MiningNet，这是一个基于 Transformer 和复制机制的神经编码器-解码器模型。

We have evaluated HintMiner on 60,000 Stack Overflow questions. The experiment results show that the proposed approach is effective. For example, HintMiner achieves an average BLEU score of 36.17% and an average ROUGE-2 score of 36.29%. Our tool and experimental data are publicly available.

我们在 60,000 个 Stack Overflow 问题上对 HintMiner 进行了评估。实验结果表明，该方法是有效的。例如，HintMiner 的平均 BLEU 得分为 36.17%，平均 ROUGE-2 得分为 36.29%。我们的工具和实验数据已公开。

---

Paper Details:

• Authors: Zhenyu Zhang, JiuDong Yang
• Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
• Journal Reference: Artificial Intelligence and Statistics, 2024
• arXiv ID: 2609.16060

论文详情：

• 作者： Zhenyu Zhang, JiuDong Yang
• 学科分类： 机器学习 (cs.LG)；人工智能 (cs.AI)；计算与语言 (cs.CL)
• 期刊参考： Artificial Intelligence and Statistics, 2024
• arXiv ID: 2609.16060