השוואת שיטות

	הסקת היגיון בריא (Commonsense Reasoning) בעיבוד שפה טבעית (NLP)	BERT Embeddings
תחום	כריית טקסט	כריית טקסט
משפחה	Process / pipeline	Process / pipeline
שנת המקור	2019 (landmark benchmarks)	2019
הוגה השיטה	Sap et al. (ATOMIC, 2019); Zellers et al. (HellaSwag, 2019)	Devlin, Chang, Lee & Toutanova (Google AI)
סוג	NLP reasoning task	Contextual transformer text-representation method
מקור מכונן	Sap, M. et al. (2019). ATOMIC: An Atlas of Machine Commonsense for If-Then Reasoning. AAAI.	Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL-HLT, 4171-4186.
כינויים	commonsense NLP, if-then reasoning, Sağduyu Akıl Yürütme (Commonsense Reasoning)	contextual embeddings, transformer embeddings, BERT Tabanlı Metin Gömülmeleri
קשורות	6	4
תקציר	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.	BERT-based text embeddings, introduced by Devlin and colleagues at Google AI in 2019, turn text into context-sensitive dense vectors using a bidirectional Transformer encoder. Because the meaning of a word shifts with its context, BERT produces richer representations than static methods such as Word2Vec or topic models like LDA.