Embeddings & taalmodellen
11 methoden in deze familie.
Uitgelicht
Automatische TekstevaluatieAutomatic text evaluation is a family of reference-based metrics used to measure the quality of machine-generated text — such as translations, summaries, or natural-language-generaBERT-inbeddingenBERT-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. BecaContrastive Learning voor NLPContrastive learning for NLP is a representation-learning technique — popularised by SimCSE (Gao et al., 2021) and Supervised Contrastive Learning (Khosla et al., 2020) — that traiDoc2VecDoc2Vec, also known as Paragraph Vector, is a representation-learning method introduced by Le and Mikolov (2014) that maps whole documents to fixed-length dense vectors. These vectDetectie van genderbias in NLPGender bias detection in NLP is a family of statistical and embedding-based methods used to measure stereotyping, representational imbalance, and occupational bias in text corpora GloVe EmbeddingsGloVe (Global Vectors for Word Representation) is a static word-embedding model introduced by Pennington, Socher and Manning (2014) that learns word vectors directly from global wo
Leesroute
De meest geraadpleegde fundamentele methoden van dit onderwerp, in de volgorde waarin ze zijn ontwikkeld — een plek om te beginnen als u hier nieuw bent.