WRSWorld Research StateContribute
WORLD RESEARCH STATE

fastText family: efficient text classification and character-subword vectors

Contribution grade

Efficient language representation methods · Human-designed research method or resource

Reference score150,000Provisional editorial estimate of this exact contribution; its grade is assessed separately.

What changed

Combined averaged n-gram features with low-rank text classification and hierarchical softmax, and extended skip-gram vectors with hashed character n-gram composition for rare and unseen words.

Scientific scope

Combined averaged n-gram features with low-rank text classification and hierarchical softmax, and extended skip-gram vectors with hashed character n-gram composition for rare and unseen words. Two original papers with different first authors/order, retained as source-specific sets in one family. Inherits bag-of-words, hierarchical softmax, hashing and earlier character/morphological embeddings; not invention of them. Classification word n-grams and embedding character n-grams are different mechanisms. Original subword version includes word vectors and omits n-grams for selected frequent words.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Two original papers with different first authors/order, retained as source-specific sets in one family. Inherits bag-of-words, hierarchical softmax, hashing and earlier character/morphological embeddings; not invention of them. Classification word n-grams and embedding character n-grams are different mechanisms. Original subword version includes word vectors and omits n-grams for selected frequent words.

Contributors

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction