Porównaj metody
Przeglądaj wybrane metody obok siebie; wiersze, które się różnią, są wyróżnione.
| Rozumowanie oparte na zdrowym rozsądku w NLP× | Konstrukcja grafu wiedzy z tekstu× | |
|---|---|---|
| Dziedzina | Eksploracja tekstu | Eksploracja tekstu |
| Rodzina | Process / pipeline | Process / pipeline |
| Rok powstania≠ | 2019 (landmark benchmarks) | — |
| Twórca≠ | Sap et al. (ATOMIC, 2019); Zellers et al. (HellaSwag, 2019) | — |
| Typ≠ | NLP reasoning task | Structured knowledge representation pipeline |
| Źródło pierwotne≠ | Sap, M. et al. (2019). ATOMIC: An Atlas of Machine Commonsense for If-Then Reasoning. AAAI. link ↗ | Hogan, A. et al. (2021). Knowledge Graphs. ACM Computing Surveys, 54(4), 1-37. DOI ↗ |
| Inne nazwy | commonsense NLP, if-then reasoning, Sağduyu Akıl Yürütme (Commonsense Reasoning) | knowledge graph, KG construction, Bilgi Grafiği Oluşturma (Knowledge Graph) |
| Pokrewne≠ | 6 | 3 |
| Podsumowanie≠ | 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. | Knowledge graph construction is a text-mining pipeline that turns unstructured text into a structured graph of entities and the relations between them. Drawing on the synthesis of Hogan et al. (2021) and the relational-machine-learning review of Nickel et al. (2016), it represents knowledge as nodes (entities such as people, places, organisations) connected by labelled edges (relations), and serves semantic search, recommendation systems, and reasoning. |
| ScholarGateZbiór danych ↗ |
|
|