fastText

2000년 도입 · 논문 240편에서 사용

fastText embeddings exploit subword information to construct word embeddings. Representations are learnt of character $n$-grams, and words represented as the sum of the $n$-gram vectors. This extends the word2vec type models with subword information. This helps the embeddings understand suffixes and prefixes. Once a word is represented using character $n$-grams, a skipgram model is trained to learn the embeddings.

출처: Enriching Word Vectors with Subword Information

소개 논문: Enriching Word Vectors with Subword Information