Metodes pierādījumu reģistrs

Natural Language Generation

Natural Language Generation (NLG) is the branch of natural language processing that automatically produces fluent, human-readable text from structured data, knowledge graphs, or semantic representations. Formalised in the classical pipeline by Reiter and Dale (2000) and surveyed comprehensively by Gatt and Krahmer (2018), NLG powers applications ranging from automated financial reporting and weather bulletins to data storytelling and conversational agents.

Sources recorded, not reviewed

Avota reģistrs

Atsauces kopētas tieši no metodes avota reģistra. Tās nenozīmē nekādu apgalvojumu līmeņa verifikāciju.

Natural Language Generation (NLG)

Taksonomiskās metodes reģistrs · process-pipeline / text-mining

Gatt, A. & Krahmer, E. (2018). Survey of the State of the Art in Natural Language Generation: Core Tasks, Applications and Evaluation. Journal of Artificial Intelligence Research, 61, 65-170. · URL
Reiter, E. & Dale, R. (2000). Building Natural Language Generation Systems. Cambridge University Press. · ISBN 9780521620369

Atvērt pilnu metodi

Kurēti apgalvojumi

Apgalvojumi saglabāti pierādījumu reģistrā, katram ar savu novērtējumu.

Vēl nav kurētu apgalvojumu

Šis skatījums neizgudro apgalvojumu novērtējumu, ja reģistrā tā nav.

Saistītās metodes

Ģenerēts no metodes grafika un parādīts kā mašīnas ieteiktas attiecības — netiek izvirzīts neviens pierādījumu apgalvojums.

Same method familyAutomatic Text Evaluationmachine-suggested · Relational suggestion, not evidence.See alsoGPT Fine-Tuningmachine-suggested · Relational suggestion, not evidence.Same method familyMachine Translationmachine-suggested · Relational suggestion, not evidence.Same method familyRetrieval-Augmented Generationmachine-suggested · Relational suggestion, not evidence.See alsoSequence-to-Sequence Modelmachine-suggested · Relational suggestion, not evidence.Same method familyText Summarizationmachine-suggested · Relational suggestion, not evidence.See alsoTransformermachine-suggested · Relational suggestion, not evidence.