SAMENVATTR, or, How to Make a Text Summarization Tool for your Language of Choice

on YouTube ↗36m

" summary

Extractive summarization uses text rank by building a sentence graph, weighting edges with BM25/TF‑IDF after stop‑word removal and stemming, and solving a PageRank eigenvector with a 0.15 damping factor. The implementation leverages Jenson, NLTK snowball stemmers and community stop‑word lists so language‑specific pieces get swapped out. Demonstrated result is saman falter, a Dutch adapter that replaces stop lists, stemmer and regex; output concatenates top‑ranked sentences until a preset word limit.

AI-written summary · about

" chapters (8)

1. 0:00SAMENVATTR intro
2. 3:52TextRank algorithm
3. 12:26TextRank as summarizer
4. 14:11Jensen Python module
5. 22:37Jensen sentence similarity
6. 26:53Adapting for non-English
7. 27:57Key takeaways
8. 28:20Q&A

" related talks

• 58mAutomatic text summarizationMasa Nekic · NDC Oslo 2019
• 31mSAMEntics : Tools for paraphrase detectionNiyati Parameswaran · Data By the Bay 2016
• 19mPhrazIt : Tool for automatic text summarizationNiyati Parameswaran · Data By the Bay 2016
• 22mEmpowering journalism-approaches to automatic text summarizationMilena Djordjevic · DSC Europe 2022
• 14mSami stopwords - How far have we gotten and why does it matter?Espen Klem · NDC Oslo 2022
• 06mHierarchical Summarization for Longform Spoken DialogDaniel Li, Thomas Chen, Lydia B. Chilton, Albert Tung · UIST 2021
• 01h 28mDocument/Sentence Similarity SolutionAde Idowu · PyData London 2022
• 35mHow does text become data?Catherine Havasi, Rob Speer · Strange Loop 2013