Salīdzināt metodes

	Teksta aizpildīšana	Nosaukuma entītiju atpazīšana (NER)	Sentimentu analīze
Nozare	Teksta ieguve	Teksta ieguve	Teksta ieguve
Saime	Process / pipeline	Process / pipeline	Process / pipeline
Izcelsmes gads	1953 (cloze); 2019 (neural span infilling)	—	—
Autors	Wilson L. Taylor (cloze procedure, 1953); modern span infilling by Zhu et al. (2019)	—	—
Tips	NLP conditional text generation task	NLP sequence-labelling task	NLP text-classification task
Pirmavots	Taylor, W.L. (1953). Cloze Procedure: A New Tool for Measuring Readability. Journalism Quarterly, 30(4), 415-433.	Nadeau, D. & Sekine, S. (2007). A survey of named entity recognition. Lingvisticae Investigationes.	Pang, B. & Lee, L. (2008). Opinion Mining and Sentiment Analysis. Foundations and Trends in Information Retrieval, 2(1-2), 1-135.
Citi nosaukumi	cloze procedure, cloze test, masked language modeling, span infilling	NER, entity tagging, Adlandırılmış Varlık Tanıma (NER)	opinion mining, polarity detection, duygu analizi
Saistītās	4	3	3
Kopsavilkums	Text infilling is a natural-language-processing task that completes missing words, phrases, or spans in a document by exploiting the surrounding context. Introduced as the cloze procedure by Wilson L. Taylor in 1953 as a readability measure, it was reformulated for neural models by Zhu et al. (2019) and is now used for data augmentation, writing assistance, and language-model evaluation.	Named entity recognition (NER) is a natural-language-processing task that automatically detects and labels entities in text — such as people, organisations, locations, and dates. Surveyed by Nadeau and Sekine (2007) and later advanced with neural architectures by Lample et al. (2016), it turns free-running text into tagged spans that downstream tools can use.	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.