Word Embeddings


Introduced by Bojanowski et al. in Enriching Word Vectors with Subword Information

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.

Source: Enriching Word Vectors with Subword Information


Paper Code Results Date Stars


Task Papers Share
Text Classification 33 7.93%
General Classification 28 6.73%
Sentence 24 5.77%
Sentiment Analysis 21 5.05%
Classification 16 3.85%
Named Entity Recognition (NER) 15 3.61%
Language Modelling 12 2.88%
Word Similarity 11 2.64%
Clustering 7 1.68%


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign