Porovnat metody

	Shrnutí textu	Shlukování dokumentů	Sémantická podobnost
Obor	Dolování textu	Dolování textu	Dolování textu
Rodina	Process / pipeline	Process / pipeline	Process / pipeline
Rok vzniku	—	—	2019
Tvůrce	—	—	Nils Reimers & Iryna Gurevych (Sentence-BERT)
Typ	NLP text-generation / text-reduction task	Unsupervised text-mining task	NLP text-comparison task
Původní zdroj	Nenkova, A. & McKeown, K. (2011). Automatic Summarization. Foundations and Trends in Information Retrieval.	Aggarwal, C. C. & Zhai, C. (2012). Mining Text Data. Springer. ISBN: 9781461432227	Reimers, N. & Gurevych, I. (2019). Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. EMNLP.
Další názvy	automatic summarization, extractive summarization, abstractive summarization, Otomatik Metin Özetleme	text clustering, unsupervised text grouping, Belge Kümeleme (Document Clustering)	semantic textual similarity, text similarity, Anlamsal Benzerlik Analizi
Příbuzné	4	4	4
Shrnutí	Automatic text summarization is a natural-language-processing task that condenses long documents into shorter summaries while preserving their key information. It works through one of two families of approaches — extractive summarization, which selects the most important spans from the source, or abstractive summarization, which generates new text. The field was consolidated by Nenkova and McKeown (2011), and sequence-to-sequence models such as BART (Lewis et al., 2020) advanced the abstractive side.	Document clustering is an unsupervised text-mining task that groups documents with similar content together without using any labels. It is used to organise large collections and for exploratory analysis, drawing on the body of text-mining techniques consolidated by Aggarwal and Zhai (2012) and compared empirically by Steinbach, Karypis and Kumar (2000).	Semantic similarity analysis measures how close in meaning two texts are, rather than how many words they share on the surface. Building on the Sentence-BERT work of Reimers and Gurevych (2019), it represents each text as a vector and compares those vectors so that paraphrases score high even when their wording differs.