When FastText Pays Attention: Efficient Estimation of Word Representations using Constrained Positional Weighting

Varování

Publikace nespadá pod Pedagogickou fakultu, ale pod Fakultu informatiky. Oficiální stránka publikace je na webu muni.cz.
Autoři

NOVOTNÝ Vít ŠTEFÁNIK Michal AYETIRAN Eniafe Festus SOJKA Petr ŘEHŮŘEK Radim

Rok publikování 2022
Druh Článek v odborném periodiku
Časopis / Zdroj Journal of Universal Computer Science
Fakulta / Pracoviště MU

Fakulta informatiky

Citace
www
Doi http://dx.doi.org/10.3897/jucs.69619
Klíčová slova Word embeddings; fastText; attention
Popis In 2018, Mikolov et al. introduced the positional language model, which has characteristics of attention-based neural machine translation models and which achieved state-of-the-art performance on the intrinsic word analogy task. However, the positional model is not practically fast and it has never been evaluated on qualitative criteria or extrinsic tasks. We propose a constrained positional model, which adapts the sparse attention mechanism from neural machine translation to improve the speed of the positional model. We evaluate the positional and constrained positional models on three novel qualitative criteria and on language modeling. We show that the positional and constrained positional models contain interpretable information about the grammatical properties of words and outperform other shallow models on language modeling. We also show that our constrained model outperforms the positional model on language modeling and trains twice as fast.
Související projekty:

Používáte starou verzi internetového prohlížeče. Doporučujeme aktualizovat Váš prohlížeč na nejnovější verzi.