Data as of Jul 25, 2026 · Based on 2,718,867 AI responses across 9,511 prompts · See how Parse measures this
BERTSUMgithub.com · Low evidencePreSumm is a text summarization toolkit implementing the EMNLP 2019 paper on using pretrained encoders for summarization. It provides both extractive and abstractive summarization models, including BERT-based variants, with support for training and evaluating on datasets like CNN/DailyMail and XSum.
Parse Score
Sources
dhiwise.com shapes more of what AI says about BERTSUM than any other source, at 100% of its citations.