Methoden vergleichen

	Allgemeinwissensbasierte Schlussfolgerung in der NLP	Fragebeantwortung (QA)
Fachgebiet	Text Mining	Text Mining
Familie	Process / pipeline	Process / pipeline
Entstehungsjahr	2019 (landmark benchmarks)	—
Urheber	Sap et al. (ATOMIC, 2019); Zellers et al. (HellaSwag, 2019)	—
Typ	NLP reasoning task	NLP text-comprehension task
Wegweisende Quelle	Sap, M. et al. (2019). ATOMIC: An Atlas of Machine Commonsense for If-Then Reasoning. AAAI.	Rajpurkar, P. et al. (2016). SQuAD: 100,000+ Questions for Machine Comprehension of Text. EMNLP.
Aliasnamen	commonsense NLP, if-then reasoning, Sağduyu Akıl Yürütme (Commonsense Reasoning)	QA, machine reading comprehension, Soru Cevaplama (Question Answering)
Verwandt	6	4
Zusammenfassung	Commonsense reasoning in NLP refers to the capacity of a language model or inference system to draw on implicit, world-knowledge facts that humans take for granted — facts not stated in the text — to answer questions, complete stories, or interpret dialogue. Landmark benchmarks formalising the task include ATOMIC (Sap et al., 2019), an if-then commonsense knowledge graph, and HellaSwag (Zellers et al., 2019), a sentence-completion challenge that exposed gaps in machine understanding of everyday events.	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.