PTM4Tag+: Tag recommendation of stack overflow posts with pre-trained models

• Main Authors: HE, Junda, XU, Bowen, YANG, Zhou, HAN, DongGyun, YANG, Chengran, LIU, Jiakun, ZHAO, Zhipeng, David LO
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2025
• Subjects: Pre-trained models; Stack overflow; Tag recommendation; Transformer; Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/9846; https://ink.library.smu.edu.sg/context/sis_research/article/10846/viewcontent/PTM4Tag__sv.pdf
• Institution: Singapore Management University

Stack Overflow is one of the most influential Software Question & Answer (SQA) websites, hosting millions of programming-related questions and answers. Tags play a critical role in efficiently organizing the contents on Stack Overflow and are vital to support various site operations, such as querying relevant content. Poorly chosen tags often lead to issues such as tag ambiguity and tag explosion. Therefore, a precise and accurate automated tag recommendation technique is needed. Inspired by the recent success of pre-trained models (PTMs) in natural language processing (NLP), we present PTM4Tag+, a tag recommendation framework for Stack Overflow posts that utilize PTMs in language modeling. PTM4Tag+ is implemented with a triplet architecture, which considers three key components of a post, i.e., Title, Description, and Code, with independent PTMs. We utilize a number of popular pre-trained models, including BERT-based models (e.g., BERT, RoBERTa, CodeBERT, BERTOverflow, and ALBERT), and encoder-decoder models (e.g., PLBART, CoTexT, and CodeT5). Our results show that leveraging CodeT5 under the PTM4Tag+ framework achieves the best performance among the eight considered PTMs and outperforms the state-of-the-art Convolutional Neural Network-based approach by a substantial margin in terms of average Precision@k, Recall@k, and F1-score@k (k ranges from 1 to 5). Specifically, CodeT5 improves the performance of F1-score@1-5 by 8.8%, 12.4%, 15.3%, 16.4%, and 16.6%, respectively. Moreover, to address the concern with inference latency, we experimented PTM4Tag+ using smaller PTM models (i.e., DistilBERT, DistilRoBERTa, CodeBERT-small, and CodeT5-small). We find that although smaller PTMs cannot outperform larger PTMs, they still maintain over 93.96% of the performance on average while reducing the mean inference time by more than 47.2%.