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

Zhenyu Zhang, JiuDong Yang
Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, PMLR 238:271-279, 2024.

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. HintMiner leverages the machine comprehension and sequence generation techniques to automatically generate hints for users’ questions. It firstly retrieve many web Q&A posts and then extract some hints from the posts using MiningNet that is built via a language model. 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. 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 at \url{https://github.com/zhangzhenyu13/HintMiner}.

Cite this Paper


BibTeX
@InProceedings{pmlr-v238-zhang24a, title = {{H}int{M}iner: Automatic Question Hints Mining From {Q}&{A} Web Posts with Language Model via Self-Supervised Learning}, author = {Zhang, Zhenyu and Yang, JiuDong}, booktitle = {Proceedings of The 27th International Conference on Artificial Intelligence and Statistics}, pages = {271--279}, year = {2024}, editor = {Dasgupta, Sanjoy and Mandt, Stephan and Li, Yingzhen}, volume = {238}, series = {Proceedings of Machine Learning Research}, month = {02--04 May}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v238/zhang24a/zhang24a.pdf}, url = {https://proceedings.mlr.press/v238/zhang24a.html}, 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. HintMiner leverages the machine comprehension and sequence generation techniques to automatically generate hints for users’ questions. It firstly retrieve many web Q&A posts and then extract some hints from the posts using MiningNet that is built via a language model. 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. 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 at \url{https://github.com/zhangzhenyu13/HintMiner}.} }
Endnote
%0 Conference Paper %T HintMiner: Automatic Question Hints Mining From Q&A Web Posts with Language Model via Self-Supervised Learning %A Zhenyu Zhang %A JiuDong Yang %B Proceedings of The 27th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2024 %E Sanjoy Dasgupta %E Stephan Mandt %E Yingzhen Li %F pmlr-v238-zhang24a %I PMLR %P 271--279 %U https://proceedings.mlr.press/v238/zhang24a.html %V 238 %X 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. HintMiner leverages the machine comprehension and sequence generation techniques to automatically generate hints for users’ questions. It firstly retrieve many web Q&A posts and then extract some hints from the posts using MiningNet that is built via a language model. 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. 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 at \url{https://github.com/zhangzhenyu13/HintMiner}.
APA
Zhang, Z. & Yang, J.. (2024). HintMiner: Automatic Question Hints Mining From Q&A Web Posts with Language Model via Self-Supervised Learning. Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 238:271-279 Available from https://proceedings.mlr.press/v238/zhang24a.html.

Related Material