arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.14602cs.CLcs.AI
收藏

预训练语言模型能为研究论文生成标题吗?

Can pre-trained language models generate titles for research papers?

Jadavpur University(贾达普大学);Indian Association for the Cultivation of Science(印度科学促进会);Techno India University(泰克诺印度大学)

Tohida Rehman, Debarshi Kumar Sanyal, Samiran Chattopadhyay

AI总结:

本文通过微调预训练语言模型(如PEGASUS-large)并利用GPT-3.5-turbo在零样本设置下从摘要生成论文标题,发现微调后的PEGASUS-large在多数指标上表现最佳,且AI生成的标题准确恰当。

摘要:

研究论文的标题以简洁的风格传达论文的主题,有时也传达其发现。想出一个合适的标题通常是一项艰巨的任务,因此,如果标题生成能够自动化,对作者将是有益的。在本文中,我们微调预训练语言模型,根据论文摘要生成标题。此外,我们在零样本设置下使用GPT-3.5-turbo生成论文标题。使用ROUGE、METEOR、MoverScore、BERTScore和SciBERTScore指标评估模型性能。我们发现,微调后的PEGASUS-large在大多数指标上优于其他模型,包括微调后的LLaMA-3-8B和GPT-3.5-turbo。我们还证明ChatGPT能为论文生成富有创意的标题。我们的观察表明,AI生成的论文标题通常是准确且恰当的。

英文摘要:

The title of a research paper communicates in a succinct style the main theme and, sometimes, the findings of the paper. Coming up with the right title is often an arduous task, and therefore, it would be beneficial to authors if title generation can be automated. In this paper, we fine-tune pre-trained language models to generate titles of papers from their abstracts. Additionally, we use GPT-3.5-turbo in a zero-shot setting to generate paper titles. The performance of the models is measured with ROUGE, METEOR, MoverScore, BERTScore and SciBERTScore metrics. We find that fine-tuned PEGASUS-large outperforms the other models, including fine-tuned LLaMA-3-8B and GPT-3.5-turbo, across most metrics. We also demonstrate that ChatGPT can generate creative titles for papers. Our observations suggest that AI-generated paper titles are generally accurate and appropriate.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑