Good things come in three: Generating SO Post Titles with Pre-Trained Models, Self Improvement and Post Ranking

• URL: http://arxiv.org/abs/2406.15633v1
• Date: Fri, 21 Jun 2024 20:18:34 GMT
• Title: Good things come in three: Generating SO Post Titles with Pre-Trained Models, Self Improvement and Post Ranking
• Authors: Duc Anh Le, Anh M. T. Bui, Phuong T. Nguyen, Davide Di Ruscio,
• Abstract summary: Stack Overflow is a prominent Q and A forum, supporting developers in seeking suitable resources on programming-related matters. Having high-quality question titles is an effective means to attract developers' attention. Research has been conducted, predominantly leveraging pre-trained models to generate titles from code snippets and problem descriptions. We present FILLER as a solution to generating Stack Overflow post titles using a fine-tuned language model with self-improvement and post ranking.
• Score: 5.874782446136913
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Stack Overflow is a prominent Q and A forum, supporting developers in seeking suitable resources on programming-related matters. Having high-quality question titles is an effective means to attract developers' attention. Unfortunately, this is often underestimated, leaving room for improvement. Research has been conducted, predominantly leveraging pre-trained models to generate titles from code snippets and problem descriptions. Yet, getting high-quality titles is still a challenging task, attributed to both the quality of the input data (e.g., containing noise and ambiguity) and inherent constraints in sequence generation models. In this paper, we present FILLER as a solution to generating Stack Overflow post titles using a fine-tuned language model with self-improvement and post ranking. Our study focuses on enhancing pre-trained language models for generating titles for Stack Overflow posts, employing a training and subsequent fine-tuning paradigm for these models. To this end, we integrate the model's predictions into the training process, enabling it to learn from its errors, thereby lessening the effects of exposure bias. Moreover, we apply a post-ranking method to produce a variety of sample candidates, subsequently selecting the most suitable one. To evaluate FILLER, we perform experiments using benchmark datasets, and the empirical findings indicate that our model provides high-quality recommendations. Moreover, it significantly outperforms all the baselines, including Code2Que, SOTitle, CCBERT, M3NSCT5, and GPT3.5-turbo. A user study also shows that FILLER provides more relevant titles, with respect to SOTitle and GPT3.5-turbo.

Related papers

• Generative Multi-modal Models are Good Class-Incremental Learners [51.5648732517187]
  We propose a novel generative multi-modal model (GMM) framework for class-incremental learning. Our approach directly generates labels for images using an adapted generative model. Under the Few-shot CIL setting, we have improved by at least 14% accuracy over all the current state-of-the-art methods with significantly less forgetting.
  arXiv  Detail & Related papers  (2024-03-27T09:21:07Z)
• Automatic Bi-modal Question Title Generation for Stack Overflow with Prompt Learning [10.76882347665857]
  An initial study aimed to automatically generate the titles by only analyzing the code snippets in the question body. We propose an approach SOTitle+ by considering bi-modal information (i.e., the code snippets and the problem descriptions) in the question body. Our corpus includes 179,119 high-quality question posts for six popular programming languages.
  arXiv  Detail & Related papers  (2024-03-06T12:58:25Z)
• Automating Human Tutor-Style Programming Feedback: Leveraging GPT-4 Tutor Model for Hint Generation and GPT-3.5 Student Model for Hint Validation [29.225823214788477]
  We investigate the role of generative AI models in providing human tutor-style programming hints. Recent works have benchmarked state-of-the-art models for various feedback generation scenarios. We develop a novel technique, GPT4Hints-GPT3.5Val, to push the limits of generative AI models.
  arXiv  Detail & Related papers  (2023-10-05T17:02:59Z)
• Large Language Models in the Workplace: A Case Study on Prompt Engineering for Job Type Classification [58.720142291102135]
  This case study investigates the task of job classification in a real-world setting. The goal is to determine whether an English-language job posting is appropriate for a graduate or entry-level position.
  arXiv  Detail & Related papers  (2023-03-13T14:09:53Z)
• Representation Learning for Stack Overflow Posts: How Far are We? [14.520780251680586]
  State-of-the-art Stack Overflow post representation models are Post2Vec and BERTOverflow. Despite their promising results, these representation methods have not been evaluated in the same experimental setting. We propose SOBERT, which employs a simple-yet-effective strategy to improve the best-performing model.
  arXiv  Detail & Related papers  (2023-03-13T04:49:06Z)
• Recitation-Augmented Language Models [85.30591349383849]
  We show that RECITE is a powerful paradigm for knowledge-intensive NLP tasks. Specifically, we show that by utilizing recitation as the intermediate step, a recite-and-answer scheme can achieve new state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-10-04T00:49:20Z)
• Diverse Title Generation for Stack Overflow Posts with Multiple Sampling Enhanced Transformer [11.03785369838242]
  We propose M$_3$NSCT5, a novel approach to automatically generate multiple post titles from the given code snippets. M$_3$NSCT5 employs the CodeT5 backbone, which is a pre-trained Transformer model having an excellent language understanding. We build a large-scale dataset with 890,000 question posts covering eight programming languages to validate the effectiveness of M$_3$NSCT5.
  arXiv  Detail & Related papers  (2022-08-24T13:10:48Z)
• DapStep: Deep Assignee Prediction for Stack Trace Error rePresentation [61.99379022383108]
  We propose new deep learning models to solve the bug triage problem. The models are based on a bidirectional recurrent neural network with attention and on a convolutional neural network. To improve the quality of ranking, we propose using additional information from version control system annotations.
  arXiv  Detail & Related papers  (2022-01-14T00:16:57Z)
• Few-Shot Named Entity Recognition: A Comprehensive Study [92.40991050806544]
  We investigate three schemes to improve the model generalization ability for few-shot settings. We perform empirical comparisons on 10 public NER datasets with various proportions of labeled data. We create new state-of-the-art results on both few-shot and training-free settings.
  arXiv  Detail & Related papers  (2020-12-29T23:43:16Z)
• KGPT: Knowledge-Grounded Pre-Training for Data-to-Text Generation [100.79870384880333]
  We propose a knowledge-grounded pre-training (KGPT) to generate knowledge-enriched text. We adopt three settings, namely fully-supervised, zero-shot, few-shot to evaluate its effectiveness. Under zero-shot setting, our model achieves over 30 ROUGE-L on WebNLG while all other baselines fail.
  arXiv  Detail & Related papers  (2020-10-05T19:59:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.