Corresponding author: Vít Novotný ( 409729@mail.muni.cz ) Corresponding author: Petr Sojka ( sojka@fi.muni.cz ) © Vít Novotný, Michal Štefánik, Eniafe Festus Ayetiran, Petr Sojka, Radim Řehůřek. This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY-ND 4.0). This license allows reusers to copy and distribute the material in any medium or format in unadapted form only, and only so long as attribution is given to the creator. The license allows for commercial use. Citation:
Novotný V, Štefánik M, Ayetiran EF, Sojka P, Řehůřek R (2022) When FastText Pays Attention: Efficient Estimation of Word Representations using Constrained Positional Weighting. JUCS - Journal of Universal Computer Science 28(2): 181-201. https://doi.org/10.3897/jucs.69619 |
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.