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

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F22%3A00124923" target="_blank" >RIV/00216224:14330/22:00124923 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.3897/jucs.69619" target="_blank" >https://doi.org/10.3897/jucs.69619</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.3897/jucs.69619" target="_blank" >10.3897/jucs.69619</a>

Result language
angličtina
Original language name
When FastText Pays Attention: Efficient Estimation of Word Representations using Constrained Positional Weighting
Original language 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.
Czech name
—
Czech description
—

Type
J<sub>imp</sub> - Article in a specialist periodical, which is included in the Web of Science database
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Publication year
2022
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)