手法を比較

	述語項関係付与（SRL）	イベント検出	質問応答 (QA)
分野	テキストマイニング	テキストマイニング	テキストマイニング
系統	Process / pipeline	Process / pipeline	Process / pipeline
提唱年	2002	—	—
提唱者	Daniel Gildea & Daniel Jurafsky	—	—
種類	NLP shallow semantic parsing task	NLP information-extraction task	NLP text-comprehension task
原典	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.	Rajpurkar, P. et al. (2016). SQuAD: 100,000+ Questions for Machine Comprehension of Text. EMNLP.
別名	SRL, shallow semantic parsing, Anlamsal Rol Etiketleme (SRL)	event extraction, Olay Tespiti (Event Detection)	QA, machine reading comprehension, Soru Cevaplama (Question Answering)
関連	3	4	4
概要	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.	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.