Embeddinger og språkmodeller
11 metoder i denne familien.
Utvalgte
Automatisk tekstevalueringAutomatic 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 EmbeddingsBERT-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. BecaKontrastiv læring for NLP – Læring av tekstrepresentasjoner gjennom kontrastContrastive 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 vectDeteksjon av kjønnsbias i 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-innleiringerGloVe (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
Lesesti
Dette emnets mest refererte grunnleggende metoder, i den rekkefølgen de ble utviklet — et sted å begynne hvis du er ny her.