Эмбеддинги и языковые модели
11 — методы этого семейства.
Избранное
Автоматическая оценка текстаAutomatic 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-generaВекторные представления BERTBERT-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. BecaКонтрастное обучение для обработки естественного языкаContrastive 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 vectОбнаружение гендерных предубеждений в НЛПGender 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 Встраивания GloVeGloVe (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
План чтения
Наиболее цитируемые фундаментальные методы этой темы в порядке их появления — отправная точка, если вы здесь впервые.