方法对比

	语义角色标注 (SRL)	事件检测	命名实体识别 (NER)	问答 (QA)
领域	文本挖掘	文本挖掘	文本挖掘	文本挖掘
方法族	Process / pipeline	Process / pipeline	Process / pipeline	Process / pipeline
起源年份	2002	—	—	—
提出者	Daniel Gildea & Daniel Jurafsky	—	—	—
类型	NLP shallow semantic parsing task	NLP information-extraction task	NLP sequence-labelling task	NLP text-comprehension task
开创性文献	Gildea, D. & Jurafsky, D. (2002). Automatic Labeling of Semantic Roles. Computational Linguistics, 28(3), 245-288.	Doddington, G. et al. (2004). The Automatic Content Extraction (ACE) Program — Tasks, Data, and Evaluation. LREC.	Nadeau, D. & Sekine, S. (2007). A survey of named entity recognition. Lingvisticae Investigationes.	Rajpurkar, P. et al. (2016). SQuAD: 100,000+ Questions for Machine Comprehension of Text. EMNLP.
别名	SRL, shallow semantic parsing, Anlamsal Rol Etiketleme (SRL)	event extraction, Olay Tespiti (Event Detection)	NER, entity tagging, Adlandırılmış Varlık Tanıma (NER)	QA, machine reading comprehension, Soru Cevaplama (Question Answering)
相关	3	4	3	4
摘要	Semantic role labeling, introduced by Gildea and Jurafsky in 2002, is a natural-language-processing task that assigns semantic roles — who did what to whom, where, when, and how — to the components around a verb (predicate) in a sentence. It turns plain text into structured predicate-argument representations and is a foundational tool for event extraction.	Event detection is a natural-language-processing information-extraction task that finds events, historical developments, and action expressions in text and classifies them by type. It grew out of the Automatic Content Extraction (ACE) program described by Doddington et al. (2004) and is widely used in news analysis and historical 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.	Question answering is a natural-language-processing task that automatically answers natural-language questions grounded in a given context passage, using either extractive or generative approaches. The task was crystallised by the SQuAD benchmark of Rajpurkar et al. (2016), and later models such as XLNet (Yang et al., 2019) pushed reading-comprehension accuracy higher.