Porovnat metody

	Otevřená extrakce informací	Analýza závislostí	Rozpoznávání pojmenovaných entit (NER)
Obor	Dolování textu	Dolování textu	Dolování textu
Rodina	Process / pipeline	Process / pipeline	Process / pipeline
Rok vzniku	2007	2003	—
Tvůrce	Banko, Cafarella, Soderland, Broadhead & Etzioni	Michael Collins (statistical models, 2003)	—
Typ	Schema-free relation-extraction task	NLP syntactic-analysis task	NLP sequence-labelling task
Původní zdroj	Banko, M., Cafarella, M. J., Soderland, S., Broadhead, M. & Etzioni, O. (2007). Open Information Extraction from the Web. Proceedings of IJCAI 2007, 2670-2676.	Collins, M. (2003). Head-Driven Statistical Models for Natural Language Parsing. Computational Linguistics, 29(4), 589-637.	Nadeau, D. & Sekine, S. (2007). A survey of named entity recognition. Lingvisticae Investigationes.
Další názvy	Open IE, OpenIE, open relation extraction, Açık Bilgi Çıkarma (Open IE)	phrase-structure parsing, constituent parsing, Kurucu Öbek Ayrıştırma (Constituency Parsing)	NER, entity tagging, Adlandırılmış Varlık Tanıma (NER)
Příbuzné	3	3	3
Shrnutí	Open Information Extraction (Open IE) is a text-mining task that automatically extracts subject-relation-object triples from text without requiring a predefined relation schema. Introduced by Banko and colleagues (2007) for extraction over the open web, it converts free-running text into structured assertions used to build knowledge graphs and to mine large text collections.	Constituency parsing is a natural-language-processing task that represents a sentence as a tree of recursively nested phrase-structure constituents — for example S → NP + VP. Building on the head-driven statistical parsing models introduced by Collins (2003) and the later neural parsers of Kitaev and colleagues (2019), it exposes the hierarchical syntactic skeleton of a sentence for grammatical pattern extraction and grammar research.	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.