Porovnat metody

	Shrnutí textu	Sémantická podobnost	Analýza sentimentu
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	NLP text-comparison task	NLP text-classification task
Původní zdroj	Nenkova, A. & McKeown, K. (2011). Automatic Summarization. Foundations and Trends in Information Retrieval.	Reimers, N. & Gurevych, I. (2019). Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. EMNLP.	Pang, B. & Lee, L. (2008). Opinion Mining and Sentiment Analysis. Foundations and Trends in Information Retrieval, 2(1-2), 1-135.
Další názvy	automatic summarization, extractive summarization, abstractive summarization, Otomatik Metin Özetleme	semantic textual similarity, text similarity, Anlamsal Benzerlik Analizi	opinion mining, polarity detection, duygu analizi
Příbuzné	4	4	3
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.	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.	Sentiment analysis, also called opinion mining, is a natural-language-processing task that detects the emotional tone of text — typically classifying it as positive, negative, or neutral. It turns unstructured opinion text into structured, quantifiable polarity signals using one of three families of approaches: sentiment lexicons, trained machine-learning classifiers, or pretrained transformer models.