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

Warning

This publication doesn't include Faculty of Sports Studies. It includes Faculty of Informatics. Official publication website can be found on muni.cz.
Authors

NOVOTNÝ Vít ŠTEFÁNIK Michal AYETIRAN Eniafe Festus SOJKA Petr ŘEHŮŘEK Radim

Year of publication 2022
Type Article in Periodical
Magazine / Source Journal of Universal Computer Science
MU Faculty or unit

Faculty of Informatics

Citation
Web
Doi http://dx.doi.org/10.3897/jucs.69619
Keywords Word embeddings; fastText; attention
Description 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.
Related projects:

You are running an old browser version. We recommend updating your browser to its latest version.

More info