English(EN) Optimizing Abstractive Summarization With Fine-Tuned PEGASUS

微调的PEGASUS模型在生成式摘要方面达到最先进水平

作者 PulseAugur 编辑部 · [2 个来源] · 2026-06-24 06:43

研究人员在XL-Sum英文语料库上微调了PEGASUS模型，以改进生成式文本摘要。该微调模型在XL-Sum英文语料库上取得了最先进的性能，ROUGE分数显著提高。具体而言，与基线mT5模型相比，ROUGE-1提高了4.04%，ROUGE-2提高了15.25%，ROUGE-L提高了3.39%。 AI

影响在XL-Sum英文语料库上为生成式摘要设定了新的基准，可能影响文本摘要的未来研究和应用。

排序理由该条目是一篇研究论文，详细介绍了在特定语料库（XL-Sum英文）上微调现有模型（PEGASUS）以在任务（生成式摘要）上获得改进性能，并使用标准指标（ROUGE）进行衡量。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.CL TIER_1 English(EN) · Sadiul Arefin Rafi, Naimur Rahman, Kazi Nazibul Islam, Ha-mim Ahmad, Farig Yousuf Sadeque · 2026-06-25 04:00

Optimizing Abstractive Summarization With Fine-Tuned PEGASUS

arXiv:2606.25462v1 Announce Type: new Abstract: Abstractive text summarization is the technique of generating a short and concise summary comprising the salient ideas of a source text without making a subset of the salient sentences from the source text. The introduction of trans…
arXiv cs.CL TIER_1 English(EN) · Farig Yousuf Sadeque · 2026-06-24 06:43

Optimizing Abstractive Summarization With Fine-Tuned PEGASUS

Abstractive text summarization is the technique of generating a short and concise summary comprising the salient ideas of a source text without making a subset of the salient sentences from the source text. The introduction of transformer models such as BART, T5, and PEGASUS has …