方法对比

	NLP中的常识推理	问答 (QA)
领域	文本挖掘	文本挖掘
方法族	Process / pipeline	Process / pipeline
起源年份	2019 (landmark benchmarks)	—
提出者	Sap et al. (ATOMIC, 2019); Zellers et al. (HellaSwag, 2019)	—
类型	NLP reasoning task	NLP text-comprehension task
开创性文献	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.
别名	commonsense NLP, if-then reasoning, Sağduyu Akıl Yürütme (Commonsense Reasoning)	QA, machine reading comprehension, Soru Cevaplama (Question Answering)
相关	6	4
摘要	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.