Summary of Can Pre-trained Language Models Generate Titles For Research Papers?, by Tohida Rehman et al.
Can pre-trained language models generate titles for research papers?
by Tohida Rehman, Debarshi Kumar Sanyal, Samiran Chattopadhyay
First submitted to arxiv on: 22 Sep 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The research presents a machine learning approach to automate title generation from abstracts of research papers. The authors fine-tune pre-trained language models, including PEGASUS-large, LLaMA-3-8B, and GPT-3.5-turbo, using ROUGE, METEOR, MoverScore, BERTScore, and SciBERTScore metrics to evaluate their performance. The study finds that fine-tuned PEGASUS-large outperforms the other models across most metrics. Additionally, ChatGPT is shown to generate creative titles for papers. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research aims to help authors by developing a way to automatically generate paper titles from abstracts. The authors use special language models and compare their performance using different scoring systems. They find that one model, PEGASUS-large, works the best most of the time. They also show that ChatGPT can create interesting title ideas for papers. |
Keywords
» Artificial intelligence » Gpt » Llama » Machine learning » Rouge
